[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"similar-wzhe06--Ad-papers":3,"tool-wzhe06--Ad-papers":64},[4,17,27,35,43,56],{"id":5,"name":6,"github_repo":7,"description_zh":8,"stars":9,"difficulty_score":10,"last_commit_at":11,"category_tags":12,"status":16},3808,"stable-diffusion-webui","AUTOMATIC1111\u002Fstable-diffusion-webui","stable-diffusion-webui 是一个基于 Gradio 构建的网页版操作界面，旨在让用户能够轻松地在本地运行和使用强大的 Stable Diffusion 图像生成模型。它解决了原始模型依赖命令行、操作门槛高且功能分散的痛点，将复杂的 AI 绘图流程整合进一个直观易用的图形化平台。\n\n无论是希望快速上手的普通创作者、需要精细控制画面细节的设计师，还是想要深入探索模型潜力的开发者与研究人员，都能从中获益。其核心亮点在于极高的功能丰富度：不仅支持文生图、图生图、局部重绘（Inpainting）和外绘（Outpainting）等基础模式，还独创了注意力机制调整、提示词矩阵、负向提示词以及“高清修复”等高级功能。此外，它内置了 GFPGAN 和 CodeFormer 等人脸修复工具，支持多种神经网络放大算法，并允许用户通过插件系统无限扩展能力。即使是显存有限的设备，stable-diffusion-webui 也提供了相应的优化选项，让高质量的 AI 艺术创作变得触手可及。",162132,3,"2026-04-05T11:01:52",[13,14,15],"开发框架","图像","Agent","ready",{"id":18,"name":19,"github_repo":20,"description_zh":21,"stars":22,"difficulty_score":23,"last_commit_at":24,"category_tags":25,"status":16},1381,"everything-claude-code","affaan-m\u002Feverything-claude-code","everything-claude-code 是一套专为 AI 编程助手（如 Claude Code、Codex、Cursor 等）打造的高性能优化系统。它不仅仅是一组配置文件，而是一个经过长期实战打磨的完整框架，旨在解决 AI 代理在实际开发中面临的效率低下、记忆丢失、安全隐患及缺乏持续学习能力等核心痛点。\n\n通过引入技能模块化、直觉增强、记忆持久化机制以及内置的安全扫描功能，everything-claude-code 能显著提升 AI 在复杂任务中的表现，帮助开发者构建更稳定、更智能的生产级 AI 代理。其独特的“研究优先”开发理念和针对 Token 消耗的优化策略，使得模型响应更快、成本更低，同时有效防御潜在的攻击向量。\n\n这套工具特别适合软件开发者、AI 研究人员以及希望深度定制 AI 工作流的技术团队使用。无论您是在构建大型代码库，还是需要 AI 协助进行安全审计与自动化测试，everything-claude-code 都能提供强大的底层支持。作为一个曾荣获 Anthropic 黑客大奖的开源项目，它融合了多语言支持与丰富的实战钩子（hooks），让 AI 真正成长为懂上",140436,2,"2026-04-05T23:32:43",[13,15,26],"语言模型",{"id":28,"name":29,"github_repo":30,"description_zh":31,"stars":32,"difficulty_score":23,"last_commit_at":33,"category_tags":34,"status":16},2271,"ComfyUI","Comfy-Org\u002FComfyUI","ComfyUI 是一款功能强大且高度模块化的视觉 AI 引擎，专为设计和执行复杂的 Stable Diffusion 图像生成流程而打造。它摒弃了传统的代码编写模式，采用直观的节点式流程图界面，让用户通过连接不同的功能模块即可构建个性化的生成管线。\n\n这一设计巧妙解决了高级 AI 绘图工作流配置复杂、灵活性不足的痛点。用户无需具备编程背景，也能自由组合模型、调整参数并实时预览效果，轻松实现从基础文生图到多步骤高清修复等各类复杂任务。ComfyUI 拥有极佳的兼容性，不仅支持 Windows、macOS 和 Linux 全平台，还广泛适配 NVIDIA、AMD、Intel 及苹果 Silicon 等多种硬件架构，并率先支持 SDXL、Flux、SD3 等前沿模型。\n\n无论是希望深入探索算法潜力的研究人员和开发者，还是追求极致创作自由度的设计师与资深 AI 绘画爱好者，ComfyUI 都能提供强大的支持。其独特的模块化架构允许社区不断扩展新功能，使其成为当前最灵活、生态最丰富的开源扩散模型工具之一，帮助用户将创意高效转化为现实。",107662,"2026-04-03T11:11:01",[13,14,15],{"id":36,"name":37,"github_repo":38,"description_zh":39,"stars":40,"difficulty_score":23,"last_commit_at":41,"category_tags":42,"status":16},3704,"NextChat","ChatGPTNextWeb\u002FNextChat","NextChat 是一款轻量且极速的 AI 助手，旨在为用户提供流畅、跨平台的大模型交互体验。它完美解决了用户在多设备间切换时难以保持对话连续性，以及面对众多 AI 模型不知如何统一管理的痛点。无论是日常办公、学习辅助还是创意激发，NextChat 都能让用户随时随地通过网页、iOS、Android、Windows、MacOS 或 Linux 端无缝接入智能服务。\n\n这款工具非常适合普通用户、学生、职场人士以及需要私有化部署的企业团队使用。对于开发者而言，它也提供了便捷的自托管方案，支持一键部署到 Vercel 或 Zeabur 等平台。\n\nNextChat 的核心亮点在于其广泛的模型兼容性，原生支持 Claude、DeepSeek、GPT-4 及 Gemini Pro 等主流大模型，让用户在一个界面即可自由切换不同 AI 能力。此外，它还率先支持 MCP（Model Context Protocol）协议，增强了上下文处理能力。针对企业用户，NextChat 提供专业版解决方案，具备品牌定制、细粒度权限控制、内部知识库整合及安全审计等功能，满足公司对数据隐私和个性化管理的高标准要求。",87618,"2026-04-05T07:20:52",[13,26],{"id":44,"name":45,"github_repo":46,"description_zh":47,"stars":48,"difficulty_score":23,"last_commit_at":49,"category_tags":50,"status":16},2268,"ML-For-Beginners","microsoft\u002FML-For-Beginners","ML-For-Beginners 是由微软推出的一套系统化机器学习入门课程，旨在帮助零基础用户轻松掌握经典机器学习知识。这套课程将学习路径规划为 12 周，包含 26 节精炼课程和 52 道配套测验，内容涵盖从基础概念到实际应用的完整流程，有效解决了初学者面对庞大知识体系时无从下手、缺乏结构化指导的痛点。\n\n无论是希望转型的开发者、需要补充算法背景的研究人员，还是对人工智能充满好奇的普通爱好者，都能从中受益。课程不仅提供了清晰的理论讲解，还强调动手实践，让用户在循序渐进中建立扎实的技能基础。其独特的亮点在于强大的多语言支持，通过自动化机制提供了包括简体中文在内的 50 多种语言版本，极大地降低了全球不同背景用户的学习门槛。此外，项目采用开源协作模式，社区活跃且内容持续更新，确保学习者能获取前沿且准确的技术资讯。如果你正寻找一条清晰、友好且专业的机器学习入门之路，ML-For-Beginners 将是理想的起点。",84991,"2026-04-05T10:45:23",[14,51,52,53,15,54,26,13,55],"数据工具","视频","插件","其他","音频",{"id":57,"name":58,"github_repo":59,"description_zh":60,"stars":61,"difficulty_score":10,"last_commit_at":62,"category_tags":63,"status":16},3128,"ragflow","infiniflow\u002Fragflow","RAGFlow 是一款领先的开源检索增强生成（RAG）引擎，旨在为大语言模型构建更精准、可靠的上下文层。它巧妙地将前沿的 RAG 技术与智能体（Agent）能力相结合，不仅支持从各类文档中高效提取知识，还能让模型基于这些知识进行逻辑推理和任务执行。\n\n在大模型应用中，幻觉问题和知识滞后是常见痛点。RAGFlow 通过深度解析复杂文档结构（如表格、图表及混合排版），显著提升了信息检索的准确度，从而有效减少模型“胡编乱造”的现象，确保回答既有据可依又具备时效性。其内置的智能体机制更进一步，使系统不仅能回答问题，还能自主规划步骤解决复杂问题。\n\n这款工具特别适合开发者、企业技术团队以及 AI 研究人员使用。无论是希望快速搭建私有知识库问答系统，还是致力于探索大模型在垂直领域落地的创新者，都能从中受益。RAGFlow 提供了可视化的工作流编排界面和灵活的 API 接口，既降低了非算法背景用户的上手门槛，也满足了专业开发者对系统深度定制的需求。作为基于 Apache 2.0 协议开源的项目，它正成为连接通用大模型与行业专有知识之间的重要桥梁。",77062,"2026-04-04T04:44:48",[15,14,13,26,54],{"id":65,"github_repo":66,"name":67,"description_en":68,"description_zh":69,"ai_summary_zh":69,"readme_en":70,"readme_zh":71,"quickstart_zh":72,"use_case_zh":73,"hero_image_url":74,"owner_login":75,"owner_name":76,"owner_avatar_url":77,"owner_bio":78,"owner_company":79,"owner_location":80,"owner_email":81,"owner_twitter":79,"owner_website":82,"owner_url":83,"languages":84,"stars":89,"forks":90,"last_commit_at":91,"license":92,"difficulty_score":93,"env_os":94,"env_gpu":94,"env_ram":94,"env_deps":95,"category_tags":98,"github_topics":99,"view_count":23,"oss_zip_url":79,"oss_zip_packed_at":79,"status":16,"created_at":107,"updated_at":108,"faqs":109,"releases":115},1328,"wzhe06\u002FAd-papers","Ad-papers","Papers on Computational Advertising","Ad-papers 是一份持续更新的“计算广告”知识地图，由一线算法工程师王喆整理并开源。它把散落在各处的顶会论文、工业界实践、优化技巧和学习笔记，按主题（CTR 预估、Embedding、实时竞价、优化算法、主题模型等）分门别类，提供可直接下载的 PDF 与代码链接，省去你四处检索、甄别版本的时间。  \n如果你正做推荐\u002F广告系统的算法研究、工程落地或策略产品，Ad-papers 能帮你快速找到从 Airbnb Embedding、阿里 DIEN 到 Google Vizier 等经典与前沿方案，并给出中文解读与实现提示。  \n亮点在于：内容随作者工作动态增删，保持“不过时”；同时附带 SparkCTR、Reco-papers 等配套代码库，方便边学边跑实验。","# 计算广告论文、学习资料、业界分享\n动态更新工作中实现或者阅读过的计算广告相关论文、学习资料和业界分享，作为自己工作的总结，也希望能为计算广告相关行业的同学带来便利。\n所有资料均来自于互联网，如有侵权，请联系王喆。同时欢迎对计算广告感兴趣的同学与我讨论相关问题，我的联系方式如下：\n* Email: wzhe06@gmail.com\n* LinkedIn: [王喆的LinkedIn](https:\u002F\u002Fwww.linkedin.com\u002Fin\u002Fzhe-wang-profile\u002F)\n* 知乎私信: [王喆的知乎](https:\u002F\u002Fwww.zhihu.com\u002Fpeople\u002Fwang-zhe-58)\n\n**会不断加入一些重要的计算广告相关论文和资料，并去掉一些过时的或者跟计算广告不太相关的论文**\n* `New!` [[Airbnb Embedding] Real-time Personalization using Embeddings for Search Ranking at Airbnb (Airbnb 2018)](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FEmbedding\u002F%5BAirbnb%20Embedding%5D%20Real-time%20Personalization%20using%20Embeddings%20for%20Search%20Ranking%20at%20Airbnb%20%28Airbnb%202018%29.pdf) \u003Cbr \u002F>\n2018 KDD best paper, Airbnb基于embeddding构建的实时搜索推荐系统\n* `New!` [[DIEN] Deep Interest Evolution Network for Click-Through Rate Prediction (Alibaba 2019)](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FDeep%20Learning%20CTR%20Prediction\u002F%5BDIEN%5D%20Deep%20Interest%20Evolution%20Network%20for%20Click-Through%20Rate%20Prediction%20%28Alibaba%202019%29.pdf) \u003Cbr \u002F>\n阿里提出的深度兴趣网络（Deep Interest Network）最新改进DIEN\n\n**其他相关资源**\n* [张伟楠的RTB Papers列表](https:\u002F\u002Fgithub.com\u002Fwnzhang\u002Frtb-papers)\u003Cbr \u002F>\n* [基于Spark MLlib的CTR预估模型(LR, FM, RF, GBDT, NN, PNN)](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FSparkCTR) \u003Cbr \u002F>\n* [推荐系统相关论文和资源列表](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FReco-papers) \u003Cbr \u002F>\n* [Honglei Zhang的推荐系统论文列表](https:\u002F\u002Fgithub.com\u002Fhongleizhang\u002FRSPapers)\n\n## 目录\n\n### Optimization Method\nOnline Optimization，Parallel SGD，FTRL等优化方法，实用并且能够给出直观解释的文章\n* [Google Vizier A Service for Black-Box Optimization](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FOptimization%20Method\u002FGoogle%20Vizier%20A%20Service%20for%20Black-Box%20Optimization.pdf) \u003Cbr \u002F>\n* [在线最优化求解(Online Optimization)-冯扬](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FOptimization%20Method\u002F%E5%9C%A8%E7%BA%BF%E6%9C%80%E4%BC%98%E5%8C%96%E6%B1%82%E8%A7%A3%28Online%20Optimization%29-%E5%86%AF%E6%89%AC.pdf) \u003Cbr \u002F>\n* [Hogwild A Lock-Free Approach to Parallelizing Stochastic Gradient Descent](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FOptimization%20Method\u002FHogwild%20A%20Lock-Free%20Approach%20to%20Parallelizing%20Stochastic%20Gradient%20Descent.pdf) \u003Cbr \u002F>\n* [Parallelized Stochastic Gradient Descent](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FOptimization%20Method\u002FParallelized%20Stochastic%20Gradient%20Descent.pdf) \u003Cbr \u002F>\n* [A Survey on Algorithms of the Regularized Convex Optimization Problem](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FOptimization%20Method\u002FA%20Survey%20on%20Algorithms%20of%20the%20Regularized%20Convex%20Optimization%20Problem.pptx) \u003Cbr \u002F>\n* [Follow-the-Regularized-Leader and Mirror Descent- Equivalence Theorems and L1 Regularization](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FOptimization%20Method\u002FFollow-the-Regularized-Leader%20and%20Mirror%20Descent-%20Equivalence%20Theorems%20and%20L1%20Regularization.pdf) \u003Cbr \u002F>\n* [A Review of Bayesian Optimization](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FOptimization%20Method\u002FA%20Review%20of%20Bayesian%20Optimization.pdf) \u003Cbr \u002F>\n* [Taking the Human Out of the Loop- A Review of Bayesian Optimization](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FOptimization%20Method\u002FTaking%20the%20Human%20Out%20of%20the%20Loop-%20A%20Review%20of%20Bayesian%20Optimization.pdf) \u003Cbr \u002F>\n* [非线性规划](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FOptimization%20Method\u002F%E9%9D%9E%E7%BA%BF%E6%80%A7%E8%A7%84%E5%88%92.doc) \u003Cbr \u002F>\n\n### Topic Model\n话题模型相关文章，PLSA，LDA，进行广告Context特征提取，创意优化经常会用到Topic Model\n* [概率语言模型及其变形系列](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FTopic%20Model\u002F%E6%A6%82%E7%8E%87%E8%AF%AD%E8%A8%80%E6%A8%A1%E5%9E%8B%E5%8F%8A%E5%85%B6%E5%8F%98%E5%BD%A2%E7%B3%BB%E5%88%97.pdf) \u003Cbr \u002F>\n* [Parameter estimation for text analysis](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FTopic%20Model\u002FParameter%20estimation%20for%20text%20analysis.pdf) \u003Cbr \u002F>\n* [LDA数学八卦](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FTopic%20Model\u002FLDA%E6%95%B0%E5%AD%A6%E5%85%AB%E5%8D%A6.pdf) \u003Cbr \u002F>\n* [Distributed Representations of Words and Phrases and their Compositionality](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FTopic%20Model\u002FDistributed%20Representations%20of%20Words%20and%20Phrases%20and%20their%20Compositionality.pdf) \u003Cbr \u002F>\n* [Dirichlet Distribution, Dirichlet Process and Dirichlet Process Mixture(PPT)](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FTopic%20Model\u002FDirichlet%20Distribution%2C%20Dirichlet%20Process%20and%20Dirichlet%20Process%20Mixture%28PPT%29.pdf) \u003Cbr \u002F>\n* [理解共轭先验](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FTopic%20Model\u002F%E7%90%86%E8%A7%A3%E5%85%B1%E8%BD%AD%E5%85%88%E9%AA%8C.pdf) \u003Cbr \u002F>\n\n### Google Three Papers\nGoogle三大篇，HDFS，MapReduce，BigTable，奠定大数据基础架构的三篇文章，任何从事大数据行业的工程师都应该了解\n* [MapReduce Simplified Data Processing on Large Clusters](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FGoogle%20Three%20Papers\u002FMapReduce%20Simplified%20Data%20Processing%20on%20Large%20Clusters.pdf) \u003Cbr \u002F>\n* [The Google File System](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FGoogle%20Three%20Papers\u002FThe%20Google%20File%20System.pdf) \u003Cbr \u002F>\n* [Bigtable A Distributed Storage System for Structured Data](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FGoogle%20Three%20Papers\u002FBigtable%20A%20Distributed%20Storage%20System%20for%20Structured%20Data.pdf) \u003Cbr \u002F>\n\n### Factorization Machines\nFM因子分解机模型的相关paper，在计算广告领域非常实用的模型\n* [FM PPT by CMU](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FFactorization%20Machines\u002FFM%20PPT%20by%20CMU.pdf) \u003Cbr \u002F>\n* [Factorization Machines Rendle2010](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FFactorization%20Machines\u002FFactorization%20Machines%20Rendle2010.pdf) \u003Cbr \u002F>\n* [libfm-1.42.manual](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FFactorization%20Machines\u002Flibfm-1.42.manual.pdf) \u003Cbr \u002F>\n* [Scaling Factorization Machines to Relational Data](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FFactorization%20Machines\u002FScaling%20Factorization%20Machines%20to%20Relational%20Data.pdf) \u003Cbr \u002F>\n* [fastFM- A Library for Factorization Machines](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FFactorization%20Machines\u002FfastFM-%20A%20Library%20for%20Factorization%20Machines.pdf) \u003Cbr \u002F>\n\n### Embedding\n* [[Negative Sampling] Word2vec Explained Negative-Sampling Word-Embedding Method (2014)](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FEmbedding\u002F%5BNegative%20Sampling%5D%20Word2vec%20Explained%20Negative-Sampling%20Word-Embedding%20Method%20%282014%29.pdf) \u003Cbr \u002F>\n* [[SDNE] Structural Deep Network Embedding (THU 2016)](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FEmbedding\u002F%5BSDNE%5D%20Structural%20Deep%20Network%20Embedding%20%28THU%202016%29.pdf) \u003Cbr \u002F>\n* [[Item2Vec] Item2Vec-Neural Item Embedding for Collaborative Filtering (Microsoft 2016)](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FEmbedding\u002F%5BItem2Vec%5D%20Item2Vec-Neural%20Item%20Embedding%20for%20Collaborative%20Filtering%20%28Microsoft%202016%29.pdf) \u003Cbr \u002F>\n* [[Word2Vec] Distributed Representations of Words and Phrases and their Compositionality (Google 2013)](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FEmbedding\u002F%5BWord2Vec%5D%20Distributed%20Representations%20of%20Words%20and%20Phrases%20and%20their%20Compositionality%20%28Google%202013%29.pdf) \u003Cbr \u002F>\n* [[Word2Vec] Word2vec Parameter Learning Explained (UMich 2016)](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FEmbedding\u002F%5BWord2Vec%5D%20Word2vec%20Parameter%20Learning%20Explained%20%28UMich%202016%29.pdf) \u003Cbr \u002F>\n* [[Node2vec] Node2vec - Scalable Feature Learning for Networks (Stanford 2016)](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FEmbedding\u002F%5BNode2vec%5D%20Node2vec%20-%20Scalable%20Feature%20Learning%20for%20Networks%20%28Stanford%202016%29.pdf) \u003Cbr \u002F>\n* [[Graph Embedding] DeepWalk- Online Learning of Social Representations (SBU 2014)](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FEmbedding\u002F%5BGraph%20Embedding%5D%20DeepWalk-%20Online%20Learning%20of%20Social%20Representations%20%28SBU%202014%29.pdf) \u003Cbr \u002F>\n* [[Airbnb Embedding] Real-time Personalization using Embeddings for Search Ranking at Airbnb (Airbnb 2018)](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FEmbedding\u002F%5BAirbnb%20Embedding%5D%20Real-time%20Personalization%20using%20Embeddings%20for%20Search%20Ranking%20at%20Airbnb%20%28Airbnb%202018%29.pdf) \u003Cbr \u002F>\n* [[Alibaba Embedding] Billion-scale Commodity Embedding for E-commerce Recommendation in Alibaba (Alibaba 2018)](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FEmbedding\u002F%5BAlibaba%20Embedding%5D%20Billion-scale%20Commodity%20Embedding%20for%20E-commerce%20Recommendation%20in%20Alibaba%20%28Alibaba%202018%29.pdf) \u003Cbr \u002F>\n* [[Word2Vec] Efficient Estimation of Word Representations in Vector Space (Google 2013)](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FEmbedding\u002F%5BWord2Vec%5D%20Efficient%20Estimation%20of%20Word%20Representations%20in%20Vector%20Space%20%28Google%202013%29.pdf) \u003Cbr \u002F>\n* [[LINE] LINE - Large-scale Information Network Embedding (MSRA 2015)](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FEmbedding\u002F%5BLINE%5D%20LINE%20-%20Large-scale%20Information%20Network%20Embedding%20%28MSRA%202015%29.pdf) \u003Cbr \u002F>\n\n### Budget Control\n广告系统中Pacing，预算控制，以及怎么把预算控制与其他模块相结合的问题\n* [Budget Pacing for Targeted Online Advertisements at LinkedIn](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FBudget%20Control\u002FBudget%20Pacing%20for%20Targeted%20Online%20Advertisements%20at%20LinkedIn.pdf) \u003Cbr \u002F>\n* [广告系统中的智能预算控制策略](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FBudget%20Control\u002F%E5%B9%BF%E5%91%8A%E7%B3%BB%E7%BB%9F%E4%B8%AD%E7%9A%84%E6%99%BA%E8%83%BD%E9%A2%84%E7%AE%97%E6%8E%A7%E5%88%B6%E7%AD%96%E7%95%A5.pdf) \u003Cbr \u002F>\n* [Predicting Traffic of Online Advertising in Real-time Bidding Systems from Perspective of Demand-Side Platforms](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FBudget%20Control\u002FPredicting%20Traffic%20of%20Online%20Advertising%20in%20Real-time%20Bidding%20Systems%20from%20Perspective%20of%20Demand-Side%20Platforms.pdf) \u003Cbr \u002F>\n* [Real Time Bid Optimization with Smooth Budget Delivery in Online Advertising](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FBudget%20Control\u002FReal%20Time%20Bid%20Optimization%20with%20Smooth%20Budget%20Delivery%20in%20Online%20Advertising.pdf) \u003Cbr \u002F>\n* [PID控制经典培训教程](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FBudget%20Control\u002FPID%E6%8E%A7%E5%88%B6%E7%BB%8F%E5%85%B8%E5%9F%B9%E8%AE%AD%E6%95%99%E7%A8%8B.pdf) \u003Cbr \u002F>\n* [PID控制原理与控制算法](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FBudget%20Control\u002FPID%E6%8E%A7%E5%88%B6%E5%8E%9F%E7%90%86%E4%B8%8E%E6%8E%A7%E5%88%B6%E7%AE%97%E6%B3%95.doc) \u003Cbr \u002F>\n* [Smart Pacing for Effective Online Ad Campaign Optimization](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FBudget%20Control\u002FSmart%20Pacing%20for%20Effective%20Online%20Ad%20Campaign%20Optimization.pdf) \u003Cbr \u002F>\n\n### Tree Model\n树模型和基于树模型的boosting模型，树模型的效果在大部分问题上非常好，在CTR，CVR预估及特征工程方面的应用非常广\n* [Introduction to Boosted Trees](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FTree%20Model\u002FIntroduction%20to%20Boosted%20Trees.pdf) \u003Cbr \u002F>\n* [Classification and Regression Trees](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FTree%20Model\u002FClassification%20and%20Regression%20Trees.pdf) \u003Cbr \u002F>\n* [Greedy Function Approximation A Gradient Boosting Machine](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FTree%20Model\u002FGreedy%20Function%20Approximation%20A%20Gradient%20Boosting%20Machine.pdf) \u003Cbr \u002F>\n* [Classification and Regression Trees](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FTree%20Model\u002FClassification%20and%20Regression%20Trees.ppt) \u003Cbr \u002F>\n\n### Guaranteed Contracts Ads\n事实上，现在很多大的媒体主仍是合约广告系统，合约广告系统的在线分配，Yield Optimization，以及定价问题都是非常重要且有挑战性的问题\n* [A Dynamic Pricing Model for Unifying Programmatic Guarantee and Real-Time Bidding in Display Advertising](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FGuaranteed%20Contracts%20Ads\u002FA%20Dynamic%20Pricing%20Model%20for%20Unifying%20Programmatic%20Guarantee%20and%20Real-Time%20Bidding%20in%20Display%20Advertising.pdf) \u003Cbr \u002F>\n* [Pricing Guaranteed Contracts in Online Display Advertising](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FGuaranteed%20Contracts%20Ads\u002FPricing%20Guaranteed%20Contracts%20in%20Online%20Display%20Advertising.pdf) \u003Cbr \u002F>\n* [Risk-Aware Dynamic Reserve Prices of Programmatic Guarantee in Display Advertising](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FGuaranteed%20Contracts%20Ads\u002FRisk-Aware%20Dynamic%20Reserve%20Prices%20of%20Programmatic%20Guarantee%20in%20Display%20Advertising.pdf) \u003Cbr \u002F>\n* [Pricing Guidance in Ad Sale Negotiations The PrintAds Example](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FGuaranteed%20Contracts%20Ads\u002FPricing%20Guidance%20in%20Ad%20Sale%20Negotiations%20The%20PrintAds%20Example.pdf) \u003Cbr \u002F>\n* [Risk-Aware Revenue Maximization in Display Advertising](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FGuaranteed%20Contracts%20Ads\u002FRisk-Aware%20Revenue%20Maximization%20in%20Display%20Advertising.pdf) \u003Cbr \u002F>\n\n### Classic CTR Prediction\n* [[LR] Predicting Clicks - Estimating the Click-Through Rate for New Ads (Microsoft 2007)](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FClassic%20CTR%20Prediction\u002F%5BLR%5D%20Predicting%20Clicks%20-%20Estimating%20the%20Click-Through%20Rate%20for%20New%20Ads%20%28Microsoft%202007%29.pdf) \u003Cbr \u002F>\n* [[FFM] Field-aware Factorization Machines for CTR Prediction (Criteo 2016)](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FClassic%20CTR%20Prediction\u002F%5BFFM%5D%20Field-aware%20Factorization%20Machines%20for%20CTR%20Prediction%20%28Criteo%202016%29.pdf) \u003Cbr \u002F>\n* [[GBDT+LR] Practical Lessons from Predicting Clicks on Ads at Facebook (Facebook 2014)](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FClassic%20CTR%20Prediction\u002F%5BGBDT%2BLR%5D%20Practical%20Lessons%20from%20Predicting%20Clicks%20on%20Ads%20at%20Facebook%20%28Facebook%202014%29.pdf) \u003Cbr \u002F>\n* [[PS-PLM] Learning Piece-wise Linear Models from Large Scale Data for Ad Click Prediction (Alibaba 2017)](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FClassic%20CTR%20Prediction\u002F%5BPS-PLM%5D%20Learning%20Piece-wise%20Linear%20Models%20from%20Large%20Scale%20Data%20for%20Ad%20Click%20Prediction%20%28Alibaba%202017%29.pdf) \u003Cbr \u002F>\n* [[FTRL] Ad Click Prediction a View from the Trenches (Google 2013)](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FClassic%20CTR%20Prediction\u002F%5BFTRL%5D%20Ad%20Click%20Prediction%20a%20View%20from%20the%20Trenches%20%28Google%202013%29.pdf) \u003Cbr \u002F>\n* [[FM] Fast Context-aware Recommendations with Factorization Machines (UKON 2011)](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FClassic%20CTR%20Prediction\u002F%5BFM%5D%20Fast%20Context-aware%20Recommendations%20with%20Factorization%20Machines%20%28UKON%202011%29.pdf) \u003Cbr \u002F>\n\n### Bidding Strategy\n计算广告中广告定价，RTB过程中广告出价策略的相关问题\n* [Research Frontier of Real-Time Bidding based Display Advertising](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FBidding%20Strategy\u002FResearch%20Frontier%20of%20Real-Time%20Bidding%20based%20Display%20Advertising.pdf) \u003Cbr \u002F>\n* [Budget Constrained Bidding by Model-free Reinforcement Learning in Display Advertising](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FBidding%20Strategy\u002FBudget%20Constrained%20Bidding%20by%20Model-free%20Reinforcement%20Learning%20in%20Display%20Advertising.pdf) \u003Cbr \u002F>\n* [Real-Time Bidding with Multi-Agent Reinforcement Learning in Display Advertising](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FBidding%20Strategy\u002FReal-Time%20Bidding%20with%20Multi-Agent%20Reinforcement%20Learning%20in%20Display%20Advertising.pdf) \u003Cbr \u002F>\n* [Real-Time Bidding by Reinforcement Learning in Display Advertising](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FBidding%20Strategy\u002FReal-Time%20Bidding%20by%20Reinforcement%20Learning%20in%20Display%20Advertising.pdf) \u003Cbr \u002F>\n* [Combining Powers of Two Predictors in Optimizing Real-Time Bidding Strategy under Constrained Budget](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FBidding%20Strategy\u002FCombining%20Powers%20of%20Two%20Predictors%20in%20Optimizing%20Real-Time%20Bidding%20Strategy%20under%20Constrained%20Budget.pdf) \u003Cbr \u002F>\n* [Bid-aware Gradient Descent for Unbiased Learning with Censored Data in Display Advertising](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FBidding%20Strategy\u002FBid-aware%20Gradient%20Descent%20for%20Unbiased%20Learning%20with%20Censored%20Data%20in%20Display%20Advertising.pdf) \u003Cbr \u002F>\n* [Optimized Cost per Click in Taobao Display Advertising](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FBidding%20Strategy\u002FOptimized%20Cost%20per%20Click%20in%20Taobao%20Display%20Advertising.pdf) \u003Cbr \u002F>\n* [Real-Time Bidding Algorithms for Performance-Based Display Ad Allocation](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FBidding%20Strategy\u002FReal-Time%20Bidding%20Algorithms%20for%20Performance-Based%20Display%20Ad%20Allocation.pdf) \u003Cbr \u002F>\n* [Deep Reinforcement Learning for Sponsored Search Real-time Bidding](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FBidding%20Strategy\u002FDeep%20Reinforcement%20Learning%20for%20Sponsored%20Search%20Real-time%20Bidding.pdf) \u003Cbr \u002F>\n\n### Computational Advertising Architect\n广告系统的架构问题\n* [[TensorFlow Whitepaper]TensorFlow- Large-Scale Machine Learning on Heterogeneous Distributed Systems](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FComputational%20Advertising%20Architect\u002F%5BTensorFlow%20Whitepaper%5DTensorFlow-%20Large-Scale%20Machine%20Learning%20on%20Heterogeneous%20Distributed%20Systems.pdf) \u003Cbr \u002F>\n* [大数据下的广告排序技术及实践](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FComputational%20Advertising%20Architect\u002F%E5%A4%A7%E6%95%B0%E6%8D%AE%E4%B8%8B%E7%9A%84%E5%B9%BF%E5%91%8A%E6%8E%92%E5%BA%8F%E6%8A%80%E6%9C%AF%E5%8F%8A%E5%AE%9E%E8%B7%B5.pdf) \u003Cbr \u002F>\n* [美团机器学习 吃喝玩乐中的算法问题](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FComputational%20Advertising%20Architect\u002F%E7%BE%8E%E5%9B%A2%E6%9C%BA%E5%99%A8%E5%AD%A6%E4%B9%A0%20%E5%90%83%E5%96%9D%E7%8E%A9%E4%B9%90%E4%B8%AD%E7%9A%84%E7%AE%97%E6%B3%95%E9%97%AE%E9%A2%98.pdf) \u003Cbr \u002F>\n* [[Parameter Server]Scaling Distributed Machine Learning with the Parameter Server](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FComputational%20Advertising%20Architect\u002F%5BParameter%20Server%5DScaling%20Distributed%20Machine%20Learning%20with%20the%20Parameter%20Server.pdf) \u003Cbr \u002F>\n* [Display Advertising with Real-Time Bidding (RTB) and Behavioural Targeting](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FComputational%20Advertising%20Architect\u002FDisplay%20Advertising%20with%20Real-Time%20Bidding%20%28RTB%29%20and%20Behavioural%20Targeting.pdf) \u003Cbr \u002F>\n* [A Comparison of Distributed Machine Learning Platforms](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FComputational%20Advertising%20Architect\u002FA%20Comparison%20of%20Distributed%20Machine%20Learning%20Platforms.pdf) \u003Cbr \u002F>\n* [Efficient Query Evaluation using a Two-Level Retrieval Process](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FComputational%20Advertising%20Architect\u002FEfficient%20Query%20Evaluation%20using%20a%20Two-Level%20Retrieval%20Process.pdf) \u003Cbr \u002F>\n* [[TensorFlow Whitepaper]TensorFlow- A System for Large-Scale Machine Learning](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FComputational%20Advertising%20Architect\u002F%5BTensorFlow%20Whitepaper%5DTensorFlow-%20A%20System%20for%20Large-Scale%20Machine%20Learning.pdf) \u003Cbr \u002F>\n* [[Parameter Server]Parameter Server for Distributed Machine Learning](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FComputational%20Advertising%20Architect\u002F%5BParameter%20Server%5DParameter%20Server%20for%20Distributed%20Machine%20Learning.pdf) \u003Cbr \u002F>\n* [Overlapping Experiment Infrastructure More, Better, Faster Experimentation](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FComputational%20Advertising%20Architect\u002FOverlapping%20Experiment%20Infrastructure%20More%2C%20Better%2C%20Faster%20Experimentation.pdf) \u003Cbr \u002F>\n\n### Machine Learning Tutorial\n机器学习方面一些非常实用的学习资料\n* [各种回归的概念学习](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FMachine%20Learning%20Tutorial\u002F%E5%90%84%E7%A7%8D%E5%9B%9E%E5%BD%92%E7%9A%84%E6%A6%82%E5%BF%B5%E5%AD%A6%E4%B9%A0.doc) \u003Cbr \u002F>\n* [机器学习总图](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FMachine%20Learning%20Tutorial\u002F%E6%9C%BA%E5%99%A8%E5%AD%A6%E4%B9%A0%E6%80%BB%E5%9B%BE.jpg) \u003Cbr \u002F>\n* [Efficient Estimation of Word Representations in Vector Space](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FMachine%20Learning%20Tutorial\u002FEfficient%20Estimation%20of%20Word%20Representations%20in%20Vector%20Space.pdf) \u003Cbr \u002F>\n* [Rules of Machine Learning- Best Practices for ML Engineering](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FMachine%20Learning%20Tutorial\u002FRules%20of%20Machine%20Learning-%20Best%20Practices%20for%20ML%20Engineering.pdf) \u003Cbr \u002F>\n* [An introduction to ROC analysis](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FMachine%20Learning%20Tutorial\u002FAn%20introduction%20to%20ROC%20analysis.pdf) \u003Cbr \u002F>\n* [Deep Learning Tutorial](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FMachine%20Learning%20Tutorial\u002FDeep%20Learning%20Tutorial.pdf) \u003Cbr \u002F>\n* [广义线性模型](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FMachine%20Learning%20Tutorial\u002F%E5%B9%BF%E4%B9%89%E7%BA%BF%E6%80%A7%E6%A8%A1%E5%9E%8B.ppt) \u003Cbr \u002F>\n* [贝叶斯统计学(PPT)](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FMachine%20Learning%20Tutorial\u002F%E8%B4%9D%E5%8F%B6%E6%96%AF%E7%BB%9F%E8%AE%A1%E5%AD%A6%28PPT%29.pdf) \u003Cbr \u002F>\n* [关联规则基本算法及其应用](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FMachine%20Learning%20Tutorial\u002F%E5%85%B3%E8%81%94%E8%A7%84%E5%88%99%E5%9F%BA%E6%9C%AC%E7%AE%97%E6%B3%95%E5%8F%8A%E5%85%B6%E5%BA%94%E7%94%A8.doc) \u003Cbr \u002F>\n\n### Transfer Learning\n迁移学习相关文章，计算广告中经常遇到新广告冷启动的问题，利用迁移学习能较好解决该问题\n* [[Multi-Task]An Overview of Multi-Task Learning in Deep Neural Networks](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FTransfer%20Learning\u002F%5BMulti-Task%5DAn%20Overview%20of%20Multi-Task%20Learning%20in%20Deep%20Neural%20Networks.pdf) \u003Cbr \u002F>\n* [Scalable Hands-Free Transfer Learning for Online Advertising](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FTransfer%20Learning\u002FScalable%20Hands-Free%20Transfer%20Learning%20for%20Online%20Advertising.pdf) \u003Cbr \u002F>\n* [A Survey on Transfer Learning](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FTransfer%20Learning\u002FA%20Survey%20on%20Transfer%20Learning.pdf) \u003Cbr \u002F>\n\n### Deep Learning CTR Prediction\n* [[DCN] Deep & Cross Network for Ad Click Predictions (Stanford 2017)](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FDeep%20Learning%20CTR%20Prediction\u002F%5BDCN%5D%20Deep%20%26%20Cross%20Network%20for%20Ad%20Click%20Predictions%20%28Stanford%202017%29.pdf) \u003Cbr \u002F>\n* [[Deep Crossing] Deep Crossing - Web-Scale Modeling without Manually Crafted Combinatorial Features (Microsoft 2016)](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FDeep%20Learning%20CTR%20Prediction\u002F%5BDeep%20Crossing%5D%20Deep%20Crossing%20-%20Web-Scale%20Modeling%20without%20Manually%20Crafted%20Combinatorial%20Features%20%28Microsoft%202016%29.pdf) \u003Cbr \u002F>\n* [[PNN] Product-based Neural Networks for User Response Prediction (SJTU 2016)](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FDeep%20Learning%20CTR%20Prediction\u002F%5BPNN%5D%20Product-based%20Neural%20Networks%20for%20User%20Response%20Prediction%20%28SJTU%202016%29.pdf) \u003Cbr \u002F>\n* [[DIN] Deep Interest Network for Click-Through Rate Prediction (Alibaba 2018)](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FDeep%20Learning%20CTR%20Prediction\u002F%5BDIN%5D%20Deep%20Interest%20Network%20for%20Click-Through%20Rate%20Prediction%20%28Alibaba%202018%29.pdf) \u003Cbr \u002F>\n* [[ESMM] Entire Space Multi-Task Model - An Effective Approach for Estimating Post-Click Conversion Rate (Alibaba 2018)](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FDeep%20Learning%20CTR%20Prediction\u002F%5BESMM%5D%20Entire%20Space%20Multi-Task%20Model%20-%20An%20Effective%20Approach%20for%20Estimating%20Post-Click%20Conversion%20Rate%20%28Alibaba%202018%29.pdf) \u003Cbr \u002F>\n* [[Wide & Deep] Wide & Deep Learning for Recommender Systems (Google 2016)](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FDeep%20Learning%20CTR%20Prediction\u002F%5BWide%20%26%20Deep%5D%20Wide%20%26%20Deep%20Learning%20for%20Recommender%20Systems%20%28Google%202016%29.pdf) \u003Cbr \u002F>\n* [[xDeepFM] xDeepFM - Combining Explicit and Implicit Feature Interactions for Recommender Systems (USTC 2018)](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FDeep%20Learning%20CTR%20Prediction\u002F%5BxDeepFM%5D%20xDeepFM%20-%20Combining%20Explicit%20and%20Implicit%20Feature%20Interactions%20for%20Recommender%20Systems%20%28USTC%202018%29.pdf) \u003Cbr \u002F>\n* [[Image CTR] Image Matters - Visually modeling user behaviors using Advanced Model Server (Alibaba 2018)](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FDeep%20Learning%20CTR%20Prediction\u002F%5BImage%20CTR%5D%20Image%20Matters%20-%20Visually%20modeling%20user%20behaviors%20using%20Advanced%20Model%20Server%20%28Alibaba%202018%29.pdf) \u003Cbr \u002F>\n* [[AFM] Attentional Factorization Machines - Learning the Weight of Feature Interactions via Attention Networks (ZJU 2017)](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FDeep%20Learning%20CTR%20Prediction\u002F%5BAFM%5D%20Attentional%20Factorization%20Machines%20-%20Learning%20the%20Weight%20of%20Feature%20Interactions%20via%20Attention%20Networks%20%28ZJU%202017%29.pdf) \u003Cbr \u002F>\n* [[DIEN] Deep Interest Evolution Network for Click-Through Rate Prediction (Alibaba 2019)](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FDeep%20Learning%20CTR%20Prediction\u002F%5BDIEN%5D%20Deep%20Interest%20Evolution%20Network%20for%20Click-Through%20Rate%20Prediction%20%28Alibaba%202019%29.pdf) \u003Cbr \u002F>\n* [[DSSM] Learning Deep Structured Semantic Models for Web Search using Clickthrough Data (UIUC 2013)](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FDeep%20Learning%20CTR%20Prediction\u002F%5BDSSM%5D%20Learning%20Deep%20Structured%20Semantic%20Models%20for%20Web%20Search%20using%20Clickthrough%20Data%20%28UIUC%202013%29.pdf) \u003Cbr \u002F>\n* [[FNN] Deep Learning over Multi-field Categorical Data (UCL 2016)](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FDeep%20Learning%20CTR%20Prediction\u002F%5BFNN%5D%20Deep%20Learning%20over%20Multi-field%20Categorical%20Data%20%28UCL%202016%29.pdf) \u003Cbr \u002F>\n* [[DeepFM] A Factorization-Machine based Neural Network for CTR Prediction (HIT-Huawei 2017)](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FDeep%20Learning%20CTR%20Prediction\u002F%5BDeepFM%5D%20A%20Factorization-Machine%20based%20Neural%20Network%20for%20CTR%20Prediction%20%28HIT-Huawei%202017%29.pdf) \u003Cbr \u002F>\n* [[NFM] Neural Factorization Machines for Sparse Predictive Analytics (NUS 2017)](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FDeep%20Learning%20CTR%20Prediction\u002F%5BNFM%5D%20Neural%20Factorization%20Machines%20for%20Sparse%20Predictive%20Analytics%20%28NUS%202017%29.pdf) \u003Cbr \u002F>\n\n### Exploration and Exploitation\n探索和利用，计算广告中非常经典，也是容易被大家忽视的问题，其实所有的广告系统都面临如何解决新广告主冷启动，以及在效果不好的情况下如何探索新的优质流量的问题，希望该目录下的几篇文章能够帮助到你\n* [An Empirical Evaluation of Thompson Sampling](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FExploration%20and%20Exploitation\u002FAn%20Empirical%20Evaluation%20of%20Thompson%20Sampling.pdf) \u003Cbr \u002F>\n* [Dynamic Online Pricing with Incomplete Information Using Multi-Armed Bandit Experiments](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FExploration%20and%20Exploitation\u002FDynamic%20Online%20Pricing%20with%20Incomplete%20Information%20Using%20Multi-Armed%20Bandit%20Experiments.pdf) \u003Cbr \u002F>\n* [广告系统中的探索与利用算法](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FExploration%20and%20Exploitation\u002F%E5%B9%BF%E5%91%8A%E7%B3%BB%E7%BB%9F%E4%B8%AD%E7%9A%84%E6%8E%A2%E7%B4%A2%E4%B8%8E%E5%88%A9%E7%94%A8%E7%AE%97%E6%B3%95.pdf) \u003Cbr \u002F>\n* [Finite-time Analysis of the Multiarmed Bandit Problem](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FExploration%20and%20Exploitation\u002FFinite-time%20Analysis%20of%20the%20Multiarmed%20Bandit%20Problem.pdf) \u003Cbr \u002F>\n* [A Fast and Simple Algorithm for Contextual Bandits](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FExploration%20and%20Exploitation\u002FA%20Fast%20and%20Simple%20Algorithm%20for%20Contextual%20Bandits.pdf) \u003Cbr \u002F>\n* [Customer Acquisition via Display Advertising Using MultiArmed Bandit Experiments](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FExploration%20and%20Exploitation\u002FCustomer%20Acquisition%20via%20Display%20Advertising%20Using%20MultiArmed%20Bandit%20Experiments.pdf) \u003Cbr \u002F>\n* [Mastering the game of Go with deep neural networks and tree search](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FExploration%20and%20Exploitation\u002FMastering%20the%20game%20of%20Go%20with%20deep%20neural%20networks%20and%20tree%20search.pdf) \u003Cbr \u002F>\n* [Exploring compact reinforcement-learning representations with linear regression](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FExploration%20and%20Exploitation\u002FExploring%20compact%20reinforcement-learning%20representations%20with%20linear%20regression.pdf) \u003Cbr \u002F>\n* [Incentivizting Exploration in Reinforcement Learning with Deep Predictive Models](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FExploration%20and%20Exploitation\u002FIncentivizting%20Exploration%20in%20Reinforcement%20Learning%20with%20Deep%20Predictive%20Models.pdf) \u003Cbr \u002F>\n* [Bandit Algorithms Continued- UCB1](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FExploration%20and%20Exploitation\u002FBandit%20Algorithms%20Continued-%20UCB1.pdf) \u003Cbr \u002F>\n* [A Contextual-Bandit Approach to Personalized News Article Recommendation(LinUCB)](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FExploration%20and%20Exploitation\u002FA%20Contextual-Bandit%20Approach%20to%20Personalized%20News%20Article%20Recommendation%28LinUCB%29.pdf) \u003Cbr \u002F>\n* [Exploitation and Exploration in a Performance based Contextual Advertising System](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FExploration%20and%20Exploitation\u002FExploitation%20and%20Exploration%20in%20a%20Performance%20based%20Contextual%20Advertising%20System.pdf) \u003Cbr \u002F>\n* [Bandit based Monte-Carlo Planning](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FExploration%20and%20Exploitation\u002FBandit%20based%20Monte-Carlo%20Planning.pdf) \u003Cbr \u002F>\n* [Random Forest for the Contextual Bandit Problem](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FExploration%20and%20Exploitation\u002FRandom%20Forest%20for%20the%20Contextual%20Bandit%20Problem.pdf) \u003Cbr \u002F>\n* [Unifying Count-Based Exploration and Intrinsic Motivation](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FExploration%20and%20Exploitation\u002FUnifying%20Count-Based%20Exploration%20and%20Intrinsic%20Motivation.pdf) \u003Cbr \u002F>\n* [Analysis of Thompson Sampling for the Multi-armed Bandit Problem](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FExploration%20and%20Exploitation\u002FAnalysis%20of%20Thompson%20Sampling%20for%20the%20Multi-armed%20Bandit%20Problem.pdf) \u003Cbr \u002F>\n* [Thompson Sampling PPT](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FExploration%20and%20Exploitation\u002FThompson%20Sampling%20PPT.pdf) \u003Cbr \u002F>\n* [Hierarchical Deep Reinforcement Learning- Integrating Temporal Abstraction and Intrinsic Motivation](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FExploration%20and%20Exploitation\u002FHierarchical%20Deep%20Reinforcement%20Learning-%20Integrating%20Temporal%20Abstraction%20and%20Intrinsic%20Motivation.pdf) \u003Cbr \u002F>\n* [Exploration and Exploitation Problem by Wang Zhe](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FExploration%20and%20Exploitation\u002FExploration%20and%20Exploitation%20Problem%20by%20Wang%20Zhe.pptx) \u003Cbr \u002F>\n* [Exploration exploitation in Go UCT for Monte-Carlo Go](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FExploration%20and%20Exploitation\u002FExploration%20exploitation%20in%20Go%20UCT%20for%20Monte-Carlo%20Go.pdf) \u003Cbr \u002F>\n* [对抗搜索、多臂老虎机问题、UCB算法](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FExploration%20and%20Exploitation\u002F%E5%AF%B9%E6%8A%97%E6%90%9C%E7%B4%A2%E3%80%81%E5%A4%9A%E8%87%82%E8%80%81%E8%99%8E%E6%9C%BA%E9%97%AE%E9%A2%98%E3%80%81UCB%E7%AE%97%E6%B3%95.ppt) \u003Cbr \u002F>\n* [Using Confidence Bounds for Exploitation-Exploration Trade-offs](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FExploration%20and%20Exploitation\u002FUsing%20Confidence%20Bounds%20for%20Exploitation-Exploration%20Trade-offs.pdf) \u003Cbr \u002F>\n\n### Allocation\n广告流量的分配问题\n* [An Efficient Algorithm for Allocation of Guaranteed Display Advertising](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FAllocation\u002FAn%20Efficient%20Algorithm%20for%20Allocation%20of%20Guaranteed%20Display%20Advertising.pdf) \u003Cbr \u002F>\n* [Ad Serving Using a Compact Allocation Plan](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FAllocation\u002FAd%20Serving%20Using%20a%20Compact%20Allocation%20Plan.pdf) \u003Cbr \u002F>\n","# 计算广告论文、学习资料、业界分享  \n动态更新工作中实现或者阅读过的计算广告相关论文、学习资料和业界分享，作为自己工作的总结，也希望能为计算广告相关行业的同学带来便利。  \n所有资料均来自于互联网，如有侵权，请联系王喆。同时欢迎对计算广告感兴趣的同学与我讨论相关问题，我的联系方式如下：  \n* Email: wzhe06@gmail.com  \n* LinkedIn: [王喆的LinkedIn](https:\u002F\u002Fwww.linkedin.com\u002Fin\u002Fzhe-wang-profile\u002F)  \n* 知乎私信: [王喆的知乎](https:\u002F\u002Fwww.zhihu.com\u002Fpeople\u002Fwang-zhe-58)  \n\n**会不断加入一些重要的计算广告相关论文和资料，并去掉一些过时的或者跟计算广告不太相关的论文**  \n* `New!` [[Airbnb Embedding] Real-time Personalization using Embeddings for Search Ranking at Airbnb (Airbnb 2018)](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FEmbedding\u002F%5BAirbnb%20Embedding%5D%20Real-time%20Personalization%20using%20Embeddings%20for%20Search%20Ranking%20at%20Airbnb%20%28Airbnb%202018%29.pdf) \u003Cbr \u002F>  \n2018 KDD最佳论文，Airbnb基于embedding构建的实时搜索推荐系统  \n* `New!` [[DIEN] Deep Interest Evolution Network for Click-Through Rate Prediction (Alibaba 2019)](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FDeep%20Learning%20CTR%20Prediction\u002F%5BDIEN%5D%20Deep%20Interest%20Evolution%20Network%20for%20Click-Through%20Rate%20Prediction%20%28Alibaba%202019%29.pdf) \u003Cbr \u002F>  \n阿里提出的深度兴趣网络（Deep Interest Network）最新改进DIEN  \n\n**其他相关资源**  \n* [张伟楠的RTB Papers列表](https:\u002F\u002Fgithub.com\u002Fwnzhang\u002Frtb-papers)\u003Cbr \u002F>  \n* [基于Spark MLlib的CTR预估模型(LR, FM, RF, GBDT, NN, PNN)](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FSparkCTR) \u003Cbr \u002F>  \n* [推荐系统相关论文和资源列表](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FReco-papers) \u003Cbr \u002F>  \n* [Honglei Zhang的推荐系统论文列表](https:\u002F\u002Fgithub.com\u002Fhongleizhang\u002FRSPapers)  \n\n## 目录  \n\n### Optimization Method  \n在线优化、并行SGD、FTRL等优化方法，实用并且能够给出直观解释的文章  \n* [Google Vizier A Service for Black-Box Optimization](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FOptimization%20Method\u002FGoogle%20Vizier%20A%20Service%20for%20Black-Box%20Optimization.pdf) \u003Cbr \u002F>  \n* [在线最优化求解(Online Optimization)-冯扬](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FOptimization%20Method\u002F%E5%9C%A8%E7%BA%BF%E6%9C%80%E4%BC%98%E5%8C%96%E6%B1%82%E8%A7%A3%28Online%20Optimization%29-%E5%86%AF%E6%89%AC.pdf) \u003Cbr \u002F>  \n* [Hogwild A Lock-Free Approach to Parallelizing Stochastic Gradient Descent](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FOptimization%20Method\u002FHogwild%20A%20Lock-Free%20Approach%20to%20Parallelizing%20Stochastic%20Gradient%20Descent.pdf) \u003Cbr \u002F>  \n* [Parallelized Stochastic Gradient Descent](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FOptimization%20Method\u002FParallelized%20Stochastic%20Gradient%20Descent.pdf) \u003Cbr \u002F>  \n* [A Survey on Algorithms of the Regularized Convex Optimization Problem](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FOptimization%20Method\u002FA%20Survey%20on%20Algorithms%20of%20the%20Regularized%20Convex%20Optimization%20Problem.pptx) \u003Cbr \u002F>  \n* [Follow-the-Regularized-Leader and Mirror Descent- Equivalence Theorems and L1 Regularization](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FOptimization%20Method\u002FFollow-the-Regularized-Leader%20and%20Mirror%20Descent-%20Equivalence%20Theorems%20and%20L1%20Regularization.pdf) \u003Cbr \u002F>  \n* [A Review of Bayesian Optimization](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FOptimization%20Method\u002FA%20Review%20of%20Bayesian%20Optimization.pdf) \u003Cbr \u002F>  \n* [Taking the Human Out of the Loop- A Review of Bayesian Optimization](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FOptimization%20Method\u002FTaking%20the%20Human%20Out%20of%20the%20Loop-%20A%20Review%20of%20Bayesian%20Optimization.pdf) \u003Cbr \u002F>  \n* [非线性规划](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FOptimization%20Method\u002F%E9%9D%9E%E7%BA%BF%E6%80%A7%E8%A7%84%E5%88%92.doc) \u003Cbr \u002F>  \n\n### Topic Model  \n话题模型相关文章，PLSA、LDA，进行广告Context特征提取、创意优化经常会用到Topic Model  \n* [概率语言模型及其变形系列](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FTopic%20Model\u002F%E6%A6%82%E7%8E%87%E8%AF%AD%E8%A8%80%E6%A8%A1%E5%9E%8B%E5%8F%8A%E5%85%B6%E5%8F%98%E5%BD%A2%E7%B3%BB%E5%88%97.pdf) \u003Cbr \u002F>  \n* [Parameter estimation for text analysis](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FTopic%20Model\u002FParameter%20estimation%20for%20text%20analysis.pdf) \u003Cbr \u002F>  \n* [LDA数学八卦](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FTopic%20Model\u002FLDA%E6%95%B0%E5%AD%A6%E5%85%AB%E5%8D%A6.pdf) \u003Cbr \u002F>  \n* [Distributed Representations of Words and Phrases and their Compositionality](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FTopic%20Model\u002FDistributed%20Representations%20of%20Words%20and%20Phrases%20and%20their%20Compositionality.pdf) \u003Cbr \u002F>  \n* [Dirichlet Distribution, Dirichlet Process and Dirichlet Process Mixture(PPT)](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FTopic%20Model\u002FDirichlet%20Distribution%2C%20Dirichlet%20Process%20and%20Dirichlet%20Process%20Mixture%28PPT%29.pdf) \u003Cbr \u002F>  \n* [理解共轭先验](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FTopic%20Model\u002F%E7%90%86%E8%A7%A3%E5%85%B1%E8%BD%AD%E5%85%88%E9%AA%8C.pdf) \u003Cbr \u002F>  \n\n### Google Three Papers  \nGoogle三大篇，HDFS、MapReduce、BigTable，奠定大数据基础架构的三篇文章，任何从事大数据行业的工程师都应该了解  \n* [MapReduce Simplified Data Processing on Large Clusters](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FGoogle%20Three%20Papers\u002FMapReduce%20Simplified%20Data%20Processing%20on%20Large%20Clusters.pdf) \u003Cbr \u002F>  \n* [The Google File System](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FGoogle%20Three%20Papers\u002FThe%20Google%20File%20System.pdf) \u003Cbr \u002F>  \n* [Bigtable A Distributed Storage System for Structured Data](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FGoogle%20Three%20Papers\u002FBigtable%20A%20Distributed%20Storage%20System%20for%20Structured%20Data.pdf) \u003Cbr \u002F>  \n\n### Factorization Machines  \nFM因子分解机模型的相关paper，在计算广告领域非常实用的模型  \n* [FM PPT by CMU](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FFactorization%20Machines\u002FFM%20PPT%20by%20CMU.pdf) \u003Cbr \u002F>  \n* [Factorization Machines Rendle2010](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FFactorization%20Machines\u002FFactorization%20Machines%20Rendle2010.pdf) \u003Cbr \u002F>  \n* [libfm-1.42.manual](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FFactorization%20Machines\u002Flibfm-1.42.manual.pdf) \u003Cbr \u002F>  \n* [Scaling Factorization Machines to Relational Data](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FFactorization%20Machines\u002FScaling%20Factorization%20Machines%20to%20Relational%20Data.pdf) \u003Cbr \u002F>  \n* [fastFM- A Library for Factorization Machines](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FFactorization%20Machines\u002FfastFM-%20A%20Library%20for%20Factorization%20Machines.pdf) \u003Cbr \u002F>\n\n### 嵌入\n* [[负采样] Word2vec详解——负采样词嵌入方法（2014年）](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FEmbedding\u002F%5BNegative%20Sampling%5D%20Word2vec%20Explained%20Negative-Sampling%20Word-Embedding%20Method%20%282014%29.pdf) \u003Cbr \u002F>\n* [[SDNE] 结构化深度网络嵌入（清华大学，2016年）](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FEmbedding\u002F%5BSDNE%5D%20Structural%20Deep%20Network%20Embedding%20%28THU%202016%29.pdf) \u003Cbr \u002F>\n* [[Item2Vec] Item2Vec——用于协同过滤的神经网络商品嵌入（微软，2016年）](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FEmbedding\u002F%5BItem2Vec%5D%20Item2Vec-Neural%20Item%20Embedding%20for%20Collaborative%20Filtering%20%28Microsoft%202016%29.pdf) \u003Cbr \u002F>\n* [[Word2vec] 词与短语的分布式表示及其组合性（谷歌，2013年）](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FEmbedding\u002F%5BWord2Vec%5D%20Distributed%20Representations%20of%20Words%20and%20Phrases%20and%20their%20Compositionality%20%28Google%202013%29.pdf) \u003Cbr \u002F>\n* [[Word2vec] Word2vec参数学习详解（密歇根大学，2016年）](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FEmbedding\u002F%5BWord2Vec%5D%20Word2vec%20Parameter%20Learning%20Explained%20%28UMich%202016%29.pdf) \u003Cbr \u002F>\n* [[Node2vec] Node2vec——面向网络的可扩展特征学习（斯坦福大学，2016年）](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FEmbedding\u002F%5BNode2vec%5D%20Node2vec%20-%20Scalable%20Feature%20Learning%20for%20Networks%20%28Stanford%202016%29.pdf) \u003Cbr \u002F>\n* [[图嵌入] DeepWalk——社交表征的在线学习（SBU，2014年）](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FEmbedding\u002F%5BGraph%20Embedding%5D%20DeepWalk-%20Online%20Learning%20of%20Social%20Representations%20%28SBU%202014%29.pdf) \u003Cbr \u002F>\n* [[Airbnb嵌入] Airbnb搜索排序中的嵌入实时个性化（Airbnb，2018年）](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FEmbedding\u002F%5BAirbnb%20Embedding%5D%20Real-time%20Personalization%20using%20Embeddings%20for%20Search%20Ranking%20at%20Airbnb%20%28Airbnb%202018%29.pdf) \u003Cbr \u002F>\n* [[阿里巴巴嵌入] 阿里巴巴电商推荐中的十亿级商品嵌入（阿里巴巴，2018年）](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FEmbedding\u002F%5BAlibaba%20Embedding%5D%20Billion-scale%20Commodity%20Embedding%20for%20E-commerce%20Recommendation%20in%20Alibaba%20%28Alibaba%202018%29.pdf) \u003Cbr \u002F>\n* [[Word2vec] 向量空间中词表示的有效估计（谷歌，2013年）](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FEmbedding\u002F%5BWord2Vec%5D%20Efficient%20Estimation%20of%20Word%20Representations%20in%20Vector%20Space%20%28Google%202013%29.pdf) \u003Cbr \u002F>\n* [[LINE] LINE——大规模信息网络嵌入（MSRA，2015年）](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FEmbedding\u002F%5BLINE%5D%20LINE%20-%20Large-scale%20Information%20Network%20Embedding%20%28MSRA%202015%29.pdf) \u003Cbr \u002F>\n\n### 预算控制\n广告系统中的Pacing、预算控制，以及如何将预算控制与其他模块相结合的问题\n* [领英定向在线广告的预算 pacing](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FBudget%20Control\u002FBudget%20Pacing%20for%20Targeted%20Online%20Advertisements%20at%20LinkedIn.pdf) \u003Cbr \u002F>\n* [广告系统中的智能预算控制策略](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FBudget%20Control\u002F%E5%B9%BF%E5%91%8A%E7%B3%BB%E7%BB%9F%E4%B8%AD%E7%9A%84%E6%99%BA%E8%83%BD%E9%A2%84%E7%AE%97%E6%8E%A7%E5%88%B6%E7%AD%96%E7%95%A5.pdf) \u003Cbr \u002F>\n* [从需求方平台视角预测实时竞价系统中的在线广告流量](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FBudget%20Control\u002FPredicting%20Traffic%20of%20Online%20Advertising%20in%20Real-time%20Bidding%20Systems%20from%20Perspective%20of%20Demand-Side%20Platforms.pdf) \u003Cbr \u002F>\n* [在线广告中平滑预算投放的实时出价优化](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FBudget%20Control\u002FReal%20Time%20Bid%20Optimization%20with%20Smooth%20Budget%20Delivery%20in%20Online%20Advertising.pdf) \u003Cbr \u002F>\n* [PID控制经典培训教程](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FBudget%20Control\u002FPID%E6%8E%A7%E5%88%B6%E7%BB%8F%E5%85%B8%E5%9F%B9%E8%AE%AD%E6%95%99%E7%A8%8B.pdf) \u003Cbr \u002F>\n* [PID控制原理与控制算法](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FBudget%20Control\u002FPID%E6%8E%A7%E5%88%B6%E5%8E%9F%E7%90%86%E4%B8%8E%E6%8E%A7%E5%88%B6%E7%AE%97%E6%B3%95.doc) \u003Cbr \u002F>\n* [有效优化在线广告活动的智能 pacing](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FBudget%20Control\u002FSmart%20Pacing%20for%20Effective%20Online%20Ad%20Campaign%20Optimization.pdf) \u003Cbr \u002F>\n\n### 树模型\n树模型及基于树模型的boosting模型，树模型在大多数问题上的效果都非常好，在CTR、CVR预估及特征工程方面的应用非常广泛。\n* [提升树简介](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FTree%20Model\u002FIntroduction%20to%20Boosted%20Trees.pdf) \u003Cbr \u002F>\n* [分类与回归树](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FTree%20Model\u002FClassification%20and%20Regression%20Trees.pdf) \u003Cbr \u002F>\n* [贪婪函数逼近：梯度提升机](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FTree%20Model\u002FGreedy%20Function%20Approximation%20A%20Gradient%20Boosting%20Machine.pdf) \u003Cbr \u002F>\n* [分类与回归树](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FTree%20Model\u002FClassification%20and%20Regression%20Trees.ppt) \u003Cbr \u002F>\n\n### 保证合同广告\n事实上，现在很多大的媒体主仍是合约广告系统，合约广告系统的在线分配、收益优化以及定价问题都是非常重要且有挑战性的问题。\n* [展示广告中统一程序化保证与实时竞价的动态定价模型](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FGuaranteed%20Contracts%20Ads\u002FA%20Dynamic%20Pricing%20Model%20for%20Unifying%20Programmatic%20Guarantee%20and%20Real-Time%20Bidding%20in%20Display%20Advertising.pdf) \u003Cbr \u002F>\n* [在线展示广告中的保证合同定价](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FGuaranteed%20Contracts%20Ads\u002FPricing%20Guaranteed%20Contracts%20in%20Online%20Display%20Advertising.pdf) \u003Cbr \u002F>\n* [展示广告中程序化保证的风险感知动态保留价格](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FGuaranteed%20Contracts%20Ads\u002FRisk-Aware%20Dynamic%20Reserve%20Prices%20of%20Programmatic%20Guarantee%20in%20Display%20Advertising.pdf) \u003Cbr \u002F>\n* [广告销售谈判中的定价指导——PrintAds案例](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FGuaranteed%20Contracts%20Ads\u002FPricing%20Guidance%20in%20Ad%20Sale%20Negotiations%20The%20PrintAds%20Example.pdf) \u003Cbr \u002F>\n* [展示广告中的风险感知收益最大化](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FGuaranteed%20Contracts%20Ads\u002FRisk-Aware%20Revenue%20Maximization%20in%20Display%20Advertising.pdf) \u003Cbr \u002F>\n\n### 经典点击率预测\n* [[LR] 预测点击——估算新广告的点击率（微软，2007年）](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FClassic%20CTR%20Prediction\u002F%5BLR%5D%20Predicting%20Clicks%20-%20Estimating%20the%20Click-Through%20Rate%20for%20New%20Ads%20%28Microsoft%202007%29.pdf) \u003Cbr \u002F>\n* [[FFM] 面向领域的因子分解机用于点击率预测（Criteo，2016年）](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FClassic%20CTR%20Prediction\u002F%5BFFM%5D%20Field-aware%20Factorization%20Machines%20for%20CTR%20Prediction%20%28Criteo%202016%29.pdf) \u003Cbr \u002F>\n* [[GBDT+LR] 来自Facebook广告点击预测的实践经验（Facebook，2014年）](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FClassic%20CTR%20Prediction\u002F%5BGBDT%2BLR%5D%20Practical%20Lessons%20from%20Predicting%20Clicks%20on%20Ads%20at%20Facebook%20%28Facebook%202014%29.pdf) \u003Cbr \u002F>\n* [[PS-PLM] 从大规模数据中学习分段线性模型用于广告点击预测（阿里巴巴，2017年）](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FClassic%20CTR%20Prediction\u002F%5BPS-PLM%5D%20Learning%20Piece-wise%20Linear%20Models%20from%20Large%20Scale%20Data%20for%20Ad%20Click%20Prediction%20%28Alibaba%202017%29.pdf) \u003Cbr \u002F>\n* [[FTRL] 广告点击预测：来自一线的视角（谷歌，2013年）](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FClassic%20CTR%20Prediction\u002F%5BFTRL%5D%20Ad%20Click%20Prediction%20a%20View%20from%20the%20Trenches%20%28Google%202013%29.pdf) \u003Cbr \u002F>\n* [[FM] 基于因子分解机的快速上下文感知推荐（UKON，2011年）](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FClassic%20CTR%20Prediction\u002F%5[BFM%5D%20Fast%20Context-aware%20Recommendations%20with%20Factorization%20Machines%20%28UKON%202011%29.pdf) \u003Cbr \u002F>\n\n### 竞价策略\n计算广告中的广告定价及RTB过程中广告出价策略的相关问题\n* [实时竞价展示广告研究前沿](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FBidding%20Strategy\u002FResearch%20Frontier%20of%20Real-Time%20Bidding%20based%20Display%20Advertising.pdf) \u003Cbr \u002F>\n* [展示广告中基于无模型强化学习的预算约束竞价](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FBidding%20Strategy\u002FBudget%20Constrained%20Bidding%20by%20Model-free%20Reinforcement%20Learning%20in%20Display%20Advertising.pdf) \u003Cbr \u002F>\n* [展示广告中的多智能体强化学习实时竞价](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FBidding%20Strategy\u002FReal-Time%20Bidding%20with%20Multi-Agent%20Reinforcement%20Learning%20in%20Display%20Advertising.pdf) \u003Cbr \u002F>\n* [展示广告中的强化学习实时竞价](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FBidding%20Strategy\u002FReal-Time%20Bidding%20by%20Reinforcement%20Learning%20in%20Display%20Advertising.pdf) \u003Cbr \u002F>\n* [在预算受限条件下优化实时竞价策略时结合两个预测器的力量](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FBidding%20Strategy\u002FCombining%20Powers%20of%20Two%20Predictors%20in%20Optimizing%20Real-Time%20Bidding%20Strategy%20under%20Constrained%20Budget.pdf) \u003Cbr \u002F>\n* [面向展示广告中带删失数据的无偏学习的竞价感知梯度下降](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FBidding%20Strategy\u002FBid-aware%20Gradient%20Descent%20for%20Unbiased%20Learning%20with%20Censored%20Data%20in%20Display%20Advertising.pdf) \u003Cbr \u002F>\n* [淘宝展示广告中的优化每次点击成本](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FBidding%20Strategy\u002FOptimized%20Cost%20per%20Click%20in%20Taobao%20Display%20Advertising.pdf) \u003Cbr \u002F>\n* [基于效果的展示广告投放中的实时竞价算法](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FBidding%20Strategy\u002FReal-Time%20Bidding%20Algorithms%20for%20Performance-Based%20Display%20Ad%20Allocation.pdf) \u003Cbr \u002F>\n* [用于赞助搜索实时竞价的深度强化学习](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FBidding%20Strategy\u002FDeep%20Reinforcement%20Learning%20for%20Sponsored%20Search%20Real-time%20Bidding.pdf) \u003Cbr \u002F>\n\n### 计算广告架构师\n广告系统的架构问题\n* [[TensorFlow白皮书]TensorFlow——异构分布式系统上的大规模机器学习](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FComputational%20Advertising%20Architect\u002F%5BTensorFlow%20Whitepaper%5DTensorFlow-%20Large-Scale%20Machine%20Learning%20on%20Heterogeneous%20Distributed%20Systems.pdf) \u003Cbr \u002F>\n* [大数据下的广告排序技术及实践](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FComputational%20Advertising%20Architect\u002F%E5%A4%A7%E6%95%B0%E6%8D%AE%E4%B8%8B%E7%9A%84%E5%B9%BF%E5%91%8A%E6%8E%92%E5%BA%8F%E6%8A%80%E6%9C%AF%E5%8F%8A%E5%AE%9E%E8%B7%B5.pdf) \u003Cbr \u002F>\n* [美团机器学习 吃喝玩乐中的算法问题](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FComputational%20Advertising%20Architect\u002F%E7%BE%8E%E5%9B%A2%E6%9C%BA%E5%99%A8%E5%AD%A6%E4%B9%A0%20%E5%90%83%E5%96%9D%E7%8E%A9%E4%B9%90%E4%B8%AD%E7%9A%84%E7%AE%97%E6%B3%95%E9%97%AE%E9%A2%98.pdf) \u003Cbr \u002F>\n* [[参数服务器]利用参数服务器扩展分布式机器学习](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FComputational%20Advertising%20Architect\u002F%5BParameter%20Server%5DScaling%20Distributed%20Machine%20Learning%20with%20the%20Parameter%20Server.pdf) \u003Cbr \u002F>\n* [带有实时竞价（RTB）和行为定向的展示广告](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FComputational%20Advertising%20Architect\u002FDisplay%20Advertising%20with%20Real-Time%20Bidding%20%28RTB%29%20and%20Behavioural%20Targeting.pdf) \u003Cbr \u002F>\n* [分布式机器学习平台的比较](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FComputational%20Advertising%20Architect\u002FA%20Comparison%20of%20Distributed%20Machine%20Learning%20Platforms.pdf) \u003Cbr \u002F>\n* [利用两级检索流程进行高效查询评估](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FComputational%20Advertising%20Architect\u002FEfficient%20Query%20Evaluation%20using%20a%20Two-Level%20Retrieval%20Process.pdf) \u003Cbr \u002F>\n* [[TensorFlow白皮书]TensorFlow——大规模机器学习系统](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FComputational%20Advertising%20Architect\u002F%5BTensorFlow%20Whitepaper%5DTensorFlow-%20A%20System%20for%20Large-Scale%20Machine%20Learning.pdf) \u003Cbr \u002F>\n* [[参数服务器]用于分布式机器学习的参数服务器](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FComputational%20Advertising%20Architect\u002F%5BParameter%20Server%5DParameter%20Server%20for%20Distributed%20Machine%20Learning.pdf) \u003Cbr \u002F>\n* [重叠实验基础设施：更多、更好、更快的实验](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FComputational%20Advertising%20Architect\u002FOverlapping%20Experiment%20Infrastructure%20More%2C%20Better%2C%20Faster%20Experimentation.pdf) \u003Cbr \u002F>\n\n### 机器学习教程\n机器学习方面一些非常实用的学习资料\n* [各种回归的概念学习](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FMachine%20Learning%20Tutorial\u002F%E5%90%84%E7%A7%8D%E5%9B%9E%E5%BD%92%E7%9A%84%E6%A6%82%E5%BF%B5%E5%AD%A6%E4%B9%A0.doc) \u003Cbr \u002F>\n* [机器学习总图](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FMachine%20Learning%20Tutorial\u002F%E6%9C%BA%E5%99%A8%E5%AD%A6%E4%B9%A0%E6%80%BB%E5%9B%BE.jpg) \u003Cbr \u002F>\n* [Efficient Estimation of Word Representations in Vector Space](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FMachine%20Learning%20Tutorial\u002FEfficient%20Estimation%20of%20Word%20Representations%20in%20Vector%20Space.pdf) \u003Cbr \u002F>\n* [Rules of Machine Learning- Best Practices for ML Engineering](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FMachine%20Learning%20Tutorial\u002FRules%20of%20Machine%20Learning-%20Best%20Practices%20for%20ML%20Engineering.pdf) \u003Cbr \u002F>\n* [An introduction to ROC analysis](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FMachine%20Learning%20Tutorial\u002FAn%20introduction%20to%20ROC%20analysis.pdf) \u003Cbr \u002F>\n* [Deep Learning Tutorial](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FMachine%20Learning%20Tutorial\u002FDeep%20Learning%20Tutorial.pdf) \u003Cbr \u002F>\n* [广义线性模型](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FMachine%20Learning%20Tutorial\u002F%E5%B9%BF%E4%B9%89%E7%BA%BF%E6%80%A7%E6%A8%A1%E5%9E%8B.ppt) \u003Cbr \u002F>\n* [贝叶斯统计学(PPT)](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FMachine%20Learning%20Tutorial\u002F%E8%B4%9D%E5%8F%B6%E6%96%AF%E7%BB%9F%E8%AE%A1%E5%AD%A6%28PPT%29.pdf) \u003Cbr \u002F>\n* [关联规则基本算法及其应用](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FMachine%20Learning%20Tutorial\u002F%E5%85%B3%E8%81%94%E8%A7%84%E5%88%99%E5%9F%BA%E6%9C%AC%E7%AE%97%E6%B3%95%E5%8F%8A%E5%85%B6%E5%BA%94%E7%94%A8.doc) \u003Cbr \u002F>\n\n### 迁移学习\n迁移学习相关文章，计算广告中经常遇到新广告冷启动的问题，利用迁移学习能较好解决该问题\n* [[Multi-Task]An Overview of Multi-Task Learning in Deep Neural Networks](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FTransfer%20Learning\u002F%5BMulti-Task%5DAn%20Overview%20of%20Multi-Task%20Learning%20in%20Deep%20Neural%20Networks.pdf) \u003Cbr \u002F>\n* [Scalable Hands-Free Transfer Learning for Online Advertising](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FTransfer%20Learning\u002FScalable%20Hands-Free%20Transfer%20Learning%20for%20Online%20Advertising.pdf) \u003Cbr \u002F>\n* [A Survey on Transfer Learning](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FTransfer%20Learning\u002FA%20Survey%20on%20Transfer%20Learning.pdf) \u003Cbr \u002F>\n\n### 深度学习CTR预测\n* [[DCN] Deep & Cross Network for Ad Click Predictions (Stanford 2017)](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FDeep%20Learning%20CTR%20Prediction\u002F%5BDCN%5D%20Deep%20%26%20Cross%20Network%20for%20Ad%20Click%20Predictions%20%28Stanford%202017%29.pdf) \u003Cbr \u002F>\n* [[Deep Crossing] Deep Crossing - Web-Scale Modeling without Manually Crafted Combinatorial Features (Microsoft 2016)](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FDeep%20Learning%20CTR%20Prediction\u002F%5BDeep%20Crossing%5D%20Deep%20Crossing%20-%20Web-Scale%20Modeling%20without%20Manually%20Crafted%20Combinatorial%20Features%20%28Microsoft%202016%29.pdf) \u003Cbr \u002F>\n* [[PNN] Product-based Neural Networks for User Response Prediction (SJTU 2016)](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FDeep%20Learning%20CTR%20Prediction\u002F%5BPNN%5D%20Product-based%20Neural%20Networks%20for%20User%20Response%20Prediction%20%28SJTU%202016%29.pdf) \u003Cbr \u002F>\n* [[DIN] Deep Interest Network for Click-Through Rate Prediction (Alibaba 2018)](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FDeep%20Learning%20CTR%20Prediction\u002F%5BDIN%5D%20Deep%20Interest%20Network%20for%20Click-Through%20Rate%20Prediction%20%28Alibaba%202018%29.pdf) \u003Cbr \u002F>\n* [[ESMM] Entire Space Multi-Task Model - An Effective Approach for Estimating Post-Click Conversion Rate (Alibaba 2018)](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FDeep%20Learning%20CTR%20Prediction\u002F%5[BESMM%5D%20Entire%20Space%20Multi-Task%20Model%20-%20An%20Effective%20Approach%20for%20Estimating%20Post-Click%20Conversion%20Rate%20%28Alibaba%202018%29.pdf) \u003Cbr \u002F>\n* [[Wide & Deep] Wide & Deep Learning for Recommender Systems (Google 2016)](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FDeep%20Learning%20CTR%20Prediction\u002F%5[Broad%20&%20Deep%5D%20Wide%20&%20Deep%20Learning%20for%20Recommender%20Systems%20%28Google%202016%29.pdf) \u003Cbr \u002F>\n* [[xDeepFM] xDeepFM - Combining Explicit and Implicit Feature Interactions for Recommender Systems (USTC 2018)](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FDeep%20Learning%20CTR%20Prediction\u002F%5[BxDeepFM%5D%20xDeepFM%20-%20Combining%20Explicit%20and%20Implicit%20Feature%20Interactions%20for%20Recommender%20Systems%20%28USTC%202018%29.pdf) \u003Cbr \u002F>\n* [[Image CTR] Image Matters - Visually modeling user behaviors using Advanced Model Server (Alibaba 2018)](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FDeep%20Learning%20CTR%20Prediction\u002F%5[BImage%20CTR%5D%20Image%20Matters%20-%20Visually%20modeling%20user%20behaviors%20using%20Advanced%20Model%20Server%20%28Alibaba%202018%29.pdf) \u003Cbr \u002F>\n* [[AFM] Attentional Factorization Machines - Learning the Weight of Feature Interactions via Attention Networks (ZJU 2017)](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FDeep%20Learning%20CTR%20Prediction\u002F%5[AFM%5D%20Attentional%20Factorization%20Machines%20-%20Learning%20the%20Weight%20of%20Feature%20Interactions%20via%20Attention%20Networks%20%28ZJU%202017%29.pdf) \u003Cbr \u002F>\n* [[DIEN] Deep Interest Evolution Network for Click-Through Rate Prediction (Alibaba 2019)](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FDeep%20Learning%20CTR%20Prediction\u002F%5[DIEN%5D%20Deep%20Interest%20Evolution%20Network%20for%20Click-Through%20Rate%20Prediction%20%28Alibaba%202019%29.pdf) \u003Cbr \u002F>\n* [[DSSM] Learning Deep Structured Semantic Models for Web Search using Clickthrough Data (UIUC 2013)](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FDeep%20Learning%20CTR%20Prediction\u002F%5[DSSM%5D%20Learning%20Deep%20Structured%20Semantic%20Models%20for%20Web%20Search%20using%20Clickthrough%20Data%20%28UIUC%202013%29.pdf) \u003Cbr \u002F>\n* [[FNN] Deep Learning over Multi-field Categorical Data (UCL 2016)](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FDeep%20Learning%20CTR%20Prediction\u002F%5[FNN%5D%20Deep%20Learning%20over%20Multi-field%20Categorical%20Data%20%28UCL%202016%29.pdf) \u003Cbr \u002F>\n* [[DeepFM] A Factorization-Machine based Neural Network for CTR Prediction (HIT-Huawei 2017)](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FDeep%20Learning%20CTR%20Prediction\u002F%5[DeepFM%5D%20A%20Factorization-Machine%20based%20Neural%20Network%20for%20CTR%20Prediction%20%28HIT-Huawei%202017%29.pdf) \u003Cbr \u002F>\n* [[NFM] Neural Factorization Machines for Sparse Predictive Analytics (NUS 2017)](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FDeep%20Learning%20CTR%20Prediction\u002F%5[NFM%5D%20Neural%20Factorization%20Machines%20for%20Sparse%20Predictive%20Analytics%20%28NUS%202017%29.pdf) \u003Cbr \u002F>\n\n### 探索与利用\n探索和利用，是计算广告领域中非常经典、却也容易被大家忽视的问题。实际上，所有广告系统都面临如何解决新广告主的冷启动问题，以及在效果不佳的情况下如何探索新的优质流量的问题。希望该目录下的几篇文章能够帮助到你。\n* [Thompson采样法的实证评估](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FExploration%20and%20Exploitation\u002FAn%20Empirical%20Evaluation%20of%20Thompson%20Sampling.pdf) \u003Cbr \u002F>\n* [基于多臂老虎机实验的不完全信息动态在线定价](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FExploration%20and%20Exploitation\u002FDynamic%20Online%20Pricing%20with%20Incomplete%20Information%20Using%20Multi-Armed%20Bandit%20Experiments.pdf) \u003Cbr \u002F>\n* [广告系统中的探索与利用算法](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FExploration%20and%20Exploitation\u002F%E5%B9%BF%E5%91%8A%E7%B3%BB%E7%BB%9F%E4%B8%AD%E7%9A%84%E6%8E%A2%E7%B4%A2%E4%B8%8E%E5%88%A9%E7%94%A8%E7%AE%97%E6%B3%95.pdf) \u003Cbr \u002F>\n* [多臂老虎机问题的有限时间分析](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FExploration%20and%20Exploitation\u002FFinite-time%20Analysis%20of%20the%20Multiarmed%20Bandit%20Problem.pdf) \u003Cbr \u002F>\n* [用于上下文老虎机的快速且简单的算法](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FExploration%20and%20Exploitation\u002FA%20Fast%20and%20Simple%20Algorithm%20for%20Contextual%20Bandits.pdf) \u003Cbr \u002F>\n* [利用多臂老虎机实验进行展示广告的客户获取](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FExploration%20and%20Exploitation\u002FCustomer%20Acquisition%20via%20Display%20Advertising%20Using%20MultiArmed%20Bandit%20Experiments.pdf) \u003Cbr \u002F>\n* [用深度神经网络与树搜索掌握围棋游戏](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FExploration%20and%20Exploitation\u002FMastering%20the%20game%20of%20Go%20with%20deep%20neural%20networks%20and%20tree%20search.pdf) \u003Cbr \u002F>\n* [用线性回归探索紧凑的强化学习表示](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FExploration%20and%20Exploitation\u002FExploring%20compact%20reinforcement-learning%20representations%20with%20linear%20regression.pdf) \u003Cbr \u002F>\n* [用深度预测模型激励强化学习中的探索](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FExploration%20and%20Exploitation\u002FIncentivizting%20Exploration%20in%20Reinforcement%20Learning%20with%20Deep%20Predictive%20Models.pdf) \u003Cbr \u002F>\n* [老虎机算法续——UCB1](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FExploration%20and%20Exploitation\u002FBandit%20Algorithms%20Continued-%20UCB1.pdf) \u003Cbr \u002F>\n* [基于上下文老虎机的个性化新闻文章推荐方法（LinUCB）](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FExploration%20and%20Exploitation\u002FA%20Contextual-Bandit%20Approach%20to%20Personalized%20News%20Article%20Recommendation%28LinUCB%29.pdf) \u003Cbr \u002F>\n* [基于绩效的上下文广告系统中的利用与探索](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FExploration%20and%20Exploitation\u002FExploitation%20and%20Exploration%20in%20a%20Performance%20based%20Contextual%20Advertising%20System.pdf) \u003Cbr \u002F>\n* [基于老虎机的蒙特卡洛规划](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FExploration%20and%20Exploitation\u002FBandit%20based%20Monte-Carlo%20Planning.pdf) \u003Cbr \u002F>\n* [随机森林用于上下文老虎机问题](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FExploration%20and%20Exploitation\u002FRandom%20Forest%20for%20the%20Contextual%20Bandit%20Problem.pdf) \u003Cbr \u002F>\n* [统一基于计数的探索与内在动机](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FExploration%20and%20Exploitation\u002FUnifying%20Count-Based%20Exploration%20and%20Intrinsic%20Motivation.pdf) \u003Cbr \u002F>\n* [多臂老虎机问题中Thompson采样的分析](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FExploration%20and%20Exploitation\u002FAnalysis%20of%20Thompson%20Sampling%20for%20the%20Multi-armed%20Bandit%20Problem.pdf) \u003Cbr \u002F>\n* [Thompson采样PPT](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FExploration%20and%20Exploitation\u002FThompson%20Sampling%20PPT.pdf) \u003Cbr \u002F>\n* [分层深度强化学习——整合时间抽象与内在动机](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FExploration%20and%20Exploitation\u002FHierarchical%20Deep%20Reinforcement%20Learning-%20Integrating%20Temporal%20Abstraction%20and%20Intrinsic%20Motivation.pdf) \u003Cbr \u002F>\n* [王哲关于探索与利用问题的演讲](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FExploration%20and%20Exploitation\u002FExploration%20and%20Exploitation%20Problem%20by%20Wang%20Zhe.pptx) \u003Cbr \u002F>\n* [围棋UCT中的探索与利用——用于蒙特卡洛围棋](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FExploration%20and%20Exploitation\u002FExploration%20exploitation%20in%20Go%20UCT%20for%20Monte-Carlo%20Go.pdf) \u003Cbr \u002F>\n* [对抗搜索、多臂老虎机问题、UCB算法](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FExploration%20and%20Exploitation\u002F%E5%AF%B9%E6%8A%92%E6%90%9C%E7%B4%A2%E3%80%81%E5%A4%9A%E8%87%82%E8%80%81%E8%99%8E%E6%9C%BA%E9%97%AE%E9%A2%98%E3%80%81UCB%E7%AE%97%E6%B3%95.ppt) \u003Cbr \u002F>\n* [利用置信边界进行利用-探索权衡](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FExploration%20and%20Exploitation\u002FUsing%20Confidence%20Bounds%20for%20Exploitation-Exploration%20Trade-offs.pdf) \u003Cbr \u002F>\n\n### 分配\n广告流量的分配问题\n* [保证展示广告分配的高效算法](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FAllocation\u002FAn%20Efficient%20Algorithm%20for%20Allocation%20of%20Guaranteed%20Display%20Advertising.pdf) \u003Cbr \u002F>\n* [采用紧凑分配方案的广告投放](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FAllocation\u002FAd%20Serving%20Using%20a%20Compact%20Allocation%20Plan.pdf) \u003Cbr \u002F>","# Ad-papers 快速上手指南\n\n> 计算广告领域论文、学习资料与业界分享的中文精选仓库，持续更新。\n\n---\n\n## 环境准备\n- **系统**：Windows \u002F macOS \u002F Linux 均可  \n- **依赖**：仅需浏览器或 PDF 阅读器即可阅读论文；如需本地运行示例代码，需 Python ≥ 3.7  \n- **网络**：GitHub 访问不畅时，可使用国内镜像（见下方）\n\n---\n\n## 安装步骤\n1. **克隆仓库**  \n   ```bash\n   git clone https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers.git\n   cd Ad-papers\n   ```\n   国内镜像（Gitee 同步，每日自动更新）：  \n   ```bash\n   git clone https:\u002F\u002Fgitee.com\u002Fmirrors\u002FAd-papers.git\n   cd Ad-papers\n   ```\n\n2. **（可选）安装 Python 依赖**  \n   若需运行仓库中的示例代码（如 SparkCTR）：  \n   ```bash\n   pip install -r requirements.txt\n   ```\n\n---\n\n## 基本使用\n1. **直接阅读**  \n   进入任意子目录，双击 PDF 即可阅读。例如：  \n   ```bash\n   open Embedding\u002F[Airbnb\\ Embedding]\\ Real-time\\ Personalization\\ using\\ Embeddings\\ for\\ Search\\ Ranking\\ at\\ Airbnb\\ \\(Airbnb\\ 2018\\).pdf\n   ```\n\n2. **快速定位主题**  \n   按目录浏览：  \n   ```\n   Ad-papers\u002F\n   ├── Embedding\u002F          # 各类 Embedding 论文\n   ├── Deep Learning CTR Prediction\u002F   # CTR 预估深度模型\n   ├── Budget Control\u002F     # 预算控制与 Pacing\n   └── ...\n   ```\n\n3. **在线预览（免下载）**  \n   打开 [GitHub 仓库](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers) 或 [Gitee 镜像](https:\u002F\u002Fgitee.com\u002Fmirrors\u002FAd-papers)，点击任意 PDF 即可在线预览。","一家 20 人规模的电商广告算法团队，正在把首页 Banner 位的点击率从 3% 提升到 5%，以备战 618 大促。\n\n### 没有 Ad-papers 时\n- 工程师 A 在 Google 上搜 “Airbnb embedding”，结果全是新闻稿，找不到原始论文，只能凭记忆复现，浪费两天。  \n- 新人 B 想搞懂 DIEN，却误把 DIN 的旧代码当最新版，线上 A\u002FB 测试效果反降 0.4%。  \n- 优化师 C 想调 FTRL 的超参，网上博客说法不一，团队内部各执一词，会议开了 3 小时仍无结论。  \n- 数据科学家 D 做 Topic Model 特征，只找到 2010 年的 LDA 讲义，缺少分布式实现细节，Spark 任务跑 6 小时才收敛。  \n\n### 使用 Ad-papers 后\n- 工程师 A 在 Ad-papers 里直接下载 Airbnb Embedding 原版 PDF，对照伪代码 4 小时完成复现，CTR 提升 0.7%。  \n- 新人 B 拿到 DIEN 论文 + 官方实现笔记，一眼看出与 DIN 的差异，当天就合并进主分支，A\u002FB 测试正向 1.2%。  \n- 优化师 C 翻到冯扬的《在线最优化求解》中文讲义，FTRL 学习率公式一目了然，10 分钟定好参数，会议取消。  \n- 数据科学家 D 用 Ad-papers 里的《LDA 数学八卦》和 Hogwild! 并行策略，把 Spark 任务压缩到 40 分钟，特征维度降低 60%。  \n\nAd-papers 把散落在各处的计算广告核心论文和实战笔记一站式整合，让团队少踩坑、快迭代、直接拿结果。","https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fwzhe06_Ad-papers_413e1abc.png","wzhe06","Wang Zhe","https:\u002F\u002Foss.gittoolsai.com\u002Favatars\u002Fwzhe06_0f390bbb.jpg","Engineering Manager @Bytedance\r\nComputational Advertising",null,"San Francisco Bay Area","wzhe06@gmail.com","https:\u002F\u002Fwzhe.me\u002F","https:\u002F\u002Fgithub.com\u002Fwzhe06",[85],{"name":86,"color":87,"percentage":88},"Python","#3572A5",100,4379,1185,"2026-04-05T15:19:24","MIT",1,"未说明",{"notes":96,"python":94,"dependencies":97},"本项目仅为计算广告相关论文、学习资料与业界分享的静态仓库，无代码运行需求，可直接在线阅读或下载 PDF\u002FPPT\u002FDOC 等文件，无需安装任何依赖或配置运行环境。",[],[13],[100,101,102,103,104,105,106],"computational-advertising","machine-learning","ctr-prediction","deep-learning","advertising","recommender-system","papers","2026-03-27T02:49:30.150509","2026-04-06T08:52:36.886134",[110],{"id":111,"question_zh":112,"answer_zh":113,"source_url":114},6065,"README 中的论文链接指向错误，如何修复？","PDF 文件已正确放入对应文件夹，但 README 中的链接写错了。请手动将 README 中的链接修正为实际文件路径，或直接合并已提交的 PR（PR 已包含正确链接）。","https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fissues\u002F3",[]]