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。 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：

• Email: [email protected]
• LinkedIn: 王喆的LinkedIn
• 知乎私信: 王喆的知乎

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

• New! [Airbnb Embedding] Real-time Personalization using Embeddings for Search Ranking at Airbnb (Airbnb 2018)
  2018 KDD best paper, Airbnb基于embeddding构建的实时搜索推荐系统
• New! [DIEN] Deep Interest Evolution Network for Click-Through Rate Prediction (Alibaba 2019)
  阿里提出的深度兴趣网络（Deep Interest Network）最新改进DIEN

其他相关资源

• 张伟楠的RTB Papers列表
  
• 基于Spark MLlib的CTR预估模型(LR, FM, RF, GBDT, NN, PNN)
  
• 推荐系统相关论文和资源列表
  
• Honglei Zhang的推荐系统论文列表

• [GBDT+LR] Practical Lessons from Predicting Clicks on Ads at Facebook (Facebook 2014)
  
• [FFM] Field-aware Factorization Machines for CTR Prediction (Criteo 2016)
  
• [FTRL] Ad Click Prediction a View from the Trenches (Google 2013)
  
• [LR] Predicting Clicks - Estimating the Click-Through Rate for New Ads (Microsoft 2007)
  
• [PS-PLM] Learning Piece-wise Linear Models from Large Scale Data for Ad Click Prediction (Alibaba 2017)
  
• [FM] Fast Context-aware Recommendations with Factorization Machines (UKON 2011)
  

FM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

• libfm-1.42.manual
  
• FM PPT by CMU
  
• Scaling Factorization Machines to Relational Data
  
• Factorization Machines Rendle2010
  
• fastFM- A Library for Factorization Machines
  

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

• A Fast and Simple Algorithm for Contextual Bandits
  
• Random Forest for the Contextual Bandit Problem
  
• Hierarchical Deep Reinforcement Learning- Integrating Temporal Abstraction and Intrinsic Motivation
  
• Thompson Sampling PPT
  
• Analysis of Thompson Sampling for the Multi-armed Bandit Problem
  
• Exploring compact reinforcement-learning representations with linear regression
  
• Exploitation and Exploration in a Performance based Contextual Advertising System
  
• Exploration and Exploitation Problem by Wang Zhe
  
• A Contextual-Bandit Approach to Personalized News Article Recommendation(LinUCB)
  
• Incentivizting Exploration in Reinforcement Learning with Deep Predictive Models
  
• Unifying Count-Based Exploration and Intrinsic Motivation
  
• Dynamic Online Pricing with Incomplete Information Using Multi-Armed Bandit Experiments
  
• Bandit based Monte-Carlo Planning
  
• 广告系统中的探索与利用算法
  
• Bandit Algorithms Continued- UCB1
  
• 对抗搜索、多臂老虎机问题、UCB算法
  
• Using Confidence Bounds for Exploitation-Exploration Trade-offs
  
• Finite-time Analysis of the Multiarmed Bandit Problem
  
• Customer Acquisition via Display Advertising Using MultiArmed Bandit Experiments
  
• An Empirical Evaluation of Thompson Sampling
  
• Exploration exploitation in Go UCT for Monte-Carlo Go
  
• Mastering the game of Go with deep neural networks and tree search
  

Google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

• MapReduce Simplified Data Processing on Large Clusters
  
• Bigtable A Distributed Storage System for Structured Data
  
• The Google File System
  

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

• A Survey on Transfer Learning
  
• Scalable Hands-Free Transfer Learning for Online Advertising
  
• [Multi-Task]An Overview of Multi-Task Learning in Deep Neural Networks
  

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

• 理解共轭先验
  
• 概率语言模型及其变形系列
  
• Distributed Representations of Words and Phrases and their Compositionality
  
• Dirichlet Distribution, Dirichlet Process and Dirichlet Process Mixture(PPT)
  
• Parameter estimation for text analysis
  
• LDA数学八卦
  

广告系统的架构问题

• 大数据下的广告排序技术及实践
  
• Overlapping Experiment Infrastructure More, Better, Faster Experimentation
  
• [TensorFlow Whitepaper]TensorFlow- A System for Large-Scale Machine Learning
  
• [Parameter Server]Parameter Server for Distributed Machine Learning
  
• Efficient Query Evaluation using a Two-Level Retrieval Process
  
• 美团机器学习 吃喝玩乐中的算法问题
  
• [Parameter Server]Scaling Distributed Machine Learning with the Parameter Server
  
• Display Advertising with Real-Time Bidding (RTB) and Behavioural Targeting
  
• [TensorFlow Whitepaper]TensorFlow- Large-Scale Machine Learning on Heterogeneous Distributed Systems
  
• A Comparison of Distributed Machine Learning Platforms
  

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

• Budget Pacing for Targeted Online Advertisements at LinkedIn
  
• Smart Pacing for Effective Online Ad Campaign Optimization
  
• Predicting Traffic of Online Advertising in Real-time Bidding Systems from Perspective of Demand-Side Platforms
  
• PID控制经典培训教程
  
• PID控制原理与控制算法
  
• Real Time Bid Optimization with Smooth Budget Delivery in Online Advertising
  
• 广告系统中的智能预算控制策略
  

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

• Pricing Guaranteed Contracts in Online Display Advertising
  
• Pricing Guidance in Ad Sale Negotiations The PrintAds Example
  
• Risk-Aware Dynamic Reserve Prices of Programmatic Guarantee in Display Advertising
  
• A Dynamic Pricing Model for Unifying Programmatic Guarantee and Real-Time Bidding in Display Advertising
  
• Risk-Aware Revenue Maximization in Display Advertising
  

计算广告中广告定价，RTB过程中广告出价策略的相关问题

• Bid-aware Gradient Descent for Unbiased Learning with Censored Data in Display Advertising
  
• Deep Reinforcement Learning for Sponsored Search Real-time Bidding
  
• Combining Powers of Two Predictors in Optimizing Real-Time Bidding Strategy under Constrained Budget
  
• Budget Constrained Bidding by Model-free Reinforcement Learning in Display Advertising
  
• Optimized Cost per Click in Taobao Display Advertising
  
• Real-Time Bidding by Reinforcement Learning in Display Advertising
  
• Real-Time Bidding Algorithms for Performance-Based Display Ad Allocation
  
• Real-Time Bidding with Multi-Agent Reinforcement Learning in Display Advertising
  
• Research Frontier of Real-Time Bidding based Display Advertising
  

Online Optimization，Parallel SGD，FTRL等优化方法，实用并且能够给出直观解释的文章

• Google Vizier A Service for Black-Box Optimization
  
• A Survey on Algorithms of the Regularized Convex Optimization Problem
  
• Taking the Human Out of the Loop- A Review of Bayesian Optimization
  
• A Review of Bayesian Optimization
  
• Follow-the-Regularized-Leader and Mirror Descent- Equivalence Theorems and L1 Regularization
  
• Parallelized Stochastic Gradient Descent
  
• 在线最优化求解(Online Optimization)-冯扬
  
• 非线性规划
  
• Hogwild A Lock-Free Approach to Parallelizing Stochastic Gradient Descent
  

机器学习方面一些非常实用的学习资料

• Deep Learning Tutorial
  
• 机器学习总图
  
• 各种回归的概念学习
  
• An introduction to ROC analysis
  
• Rules of Machine Learning- Best Practices for ML Engineering
  
• Efficient Estimation of Word Representations in Vector Space
  
• 贝叶斯统计学(PPT)
  
• 关联规则基本算法及其应用
  
• 广义线性模型
  

广告流量的分配问题

• An Efficient Algorithm for Allocation of Guaranteed Display Advertising
  
• Ad Serving Using a Compact Allocation Plan
  

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

• Introduction to Boosted Trees
  
• Classification and Regression Trees
  
• Greedy Function Approximation A Gradient Boosting Machine
  
• Classification and Regression Trees
  

• [Word2Vec] Word2vec Parameter Learning Explained (UMich 2016)
  
• [Item2Vec] Item2Vec-Neural Item Embedding for Collaborative Filtering (Microsoft 2016)
  
• [Struc2Vec] struc2vec - Learning Node Representations from StructuralIdentity
  
• [Word2Vec] Distributed Representations of Words and Phrases and their Compositionality (Google 2013)
  
• [LINE] LINE - Large-scale Information Network Embedding (MSRA 2015)
  
• [SDNE] Structural Deep Network Embedding (THU 2016)
  
• [Airbnb Embedding] Real-time Personalization using Embeddings for Search Ranking at Airbnb (Airbnb 2018)
  
• [Word2Vec] Efficient Estimation of Word Representations in Vector Space (Google 2013)
  
• [Alibaba Embedding] Billion-scale Commodity Embedding for E-commerce Recommendation in Alibaba (Alibaba 2018)
  
• [Node2vec] Node2vec - Scalable Feature Learning for Networks (Stanford 2016)
  
• [Negative Sampling] Word2vec Explained Negative-Sampling Word-Embedding Method (2014)
  
• [Graph Embedding] DeepWalk- Online Learning of Social Representations (SBU 2014)
  

• [ESMM] Entire Space Multi-Task Model - An Effective Approach for Estimating Post-Click Conversion Rate (Alibaba 2018)
  
• [DCN] Deep & Cross Network for Ad Click Predictions (Stanford 2017)
  
• [Deep Crossing] Deep Crossing - Web-Scale Modeling without Manually Crafted Combinatorial Features (Microsoft 2016)
  
• [PNN] Product-based Neural Networks for User Response Prediction (SJTU 2016)
  
• [Image CTR] Image Matters - Visually modeling user behaviors using Advanced Model Server (Alibaba 2018)
  
• [DSSM] Learning Deep Structured Semantic Models for Web Search using Clickthrough Data (UIUC 2013)
  
• [xDeepFM] xDeepFM - Combining Explicit and Implicit Feature Interactions for Recommender Systems (USTC 2018)
  
• [DeepFM] A Factorization-Machine based Neural Network for CTR Prediction (HIT-Huawei 2017)
  
• [FNN] Deep Learning over Multi-field Categorical Data (UCL 2016)
  
• [AFM] Attentional Factorization Machines - Learning the Weight of Feature Interactions via Attention Networks (ZJU 2017)
  
• [Wide & Deep] Wide & Deep Learning for Recommender Systems (Google 2016)
  
• [DIEN] Deep Interest Evolution Network for Click-Through Rate Prediction (Alibaba 2019)
  
• [NFM] Neural Factorization Machines for Sparse Predictive Analytics (NUS 2017)
  
• [DIN] Deep Interest Network for Click-Through Rate Prediction (Alibaba 2018)