计算广告论文、学习资料、业界分享

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

目录
Optimization Method

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

Topic Model

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

Google Three Papers

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
* The Google File System
* Bigtable A Distributed Storage System for Structured Data

Factorization Machines

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

Embedding

• [Negative Sampling] Word2vec Explained Negative-Sampling Word-Embedding Method (2014)


• [SDNE] Structural Deep Network Embedding (THU 2016)


• [Item2Vec] Item2Vec-Neural Item Embedding for Collaborative Filtering (Microsoft 2016)


• [Word2Vec] Distributed Representations of Words and Phrases and their Compositionality (Google 2013)


• [Word2Vec] Word2vec Parameter Learning Explained (UMich 2016)


• [Node2vec] Node2vec - Scalable Feature Learning for Networks (Stanford 2016)


• [Graph Embedding] DeepWalk- Online Learning of Social Representations (SBU 2014)


• [Airbnb Embedding] Real-time Personalization using Embeddings for Search Ranking at Airbnb (Airbnb 2018)


• [Alibaba Embedding] Billion-scale Commodity Embedding for E-commerce Recommendation in Alibaba (Alibaba 2018)


• [Word2Vec] Efficient Estimation of Word Representations in Vector Space (Google 2013)


• [LINE] LINE - Large-scale Information Network Embedding (MSRA 2015)

Budget Control

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

Tree Model

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

Guaranteed Contracts Ads

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

Classic CTR Prediction

• [LR] Predicting Clicks - Estimating the Click-Through Rate for New Ads (Microsoft 2007)


• [FFM] Field-aware Factorization Machines for CTR Prediction (Criteo 2016)


• [GBDT+LR] Practical Lessons from Predicting Clicks on Ads at Facebook (Facebook 2014)


• [PS-PLM] Learning Piece-wise Linear Models from Large Scale Data for Ad Click Prediction (Alibaba 2017)


• [FTRL] Ad Click Prediction a View from the Trenches (Google 2013)


• [FM] Fast Context-aware Recommendations with Factorization Machines (UKON 2011)

Bidding Strategy

计算广告中广告定价，RTB过程中广告出价策略的相关问题
* Research Frontier of Real-Time Bidding based Display Advertising
* Budget Constrained Bidding by Model-free Reinforcement Learning in Display Advertising
* Real-Time Bidding with Multi-Agent Reinforcement Learning in Display Advertising
* Real-Time Bidding by Reinforcement Learning in Display Advertising
* Combining Powers of Two Predictors in Optimizing Real-Time Bidding Strategy under Constrained Budget
* Bid-aware Gradient Descent for Unbiased Learning with Censored Data in Display Advertising
* Optimized Cost per Click in Taobao Display Advertising
* Real-Time Bidding Algorithms for Performance-Based Display Ad Allocation
* Deep Reinforcement Learning for Sponsored Search Real-time Bidding

Computational Advertising Architect

广告系统的架构问题
* [TensorFlow Whitepaper]TensorFlow- Large-Scale Machine Learning on Heterogeneous Distributed Systems
* 大数据下的广告排序技术及实践
* 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
* A Comparison of Distributed Machine Learning Platforms
* Efficient Query Evaluation using a Two-Level Retrieval Process
* [TensorFlow Whitepaper]TensorFlow- A System for Large-Scale Machine Learning
* [Parameter Server]Parameter Server for Distributed Machine Learning
* Overlapping Experiment Infrastructure More, Better, Faster Experimentation

Machine Learning Tutorial

机器学习方面一些非常实用的学习资料
* 各种回归的概念学习
* 机器学习总图
* Efficient Estimation of Word Representations in Vector Space
* Rules of Machine Learning- Best Practices for ML Engineering
* An introduction to ROC analysis
* Deep Learning Tutorial
* 广义线性模型
* 贝叶斯统计学(PPT)
* 关联规则基本算法及其应用

Transfer Learning

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

Deep Learning CTR Prediction

• [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)


• [DIN] Deep Interest Network for Click-Through Rate Prediction (Alibaba 2018)


• [ESMM] Entire Space Multi-Task Model - An Effective Approach for Estimating Post-Click Conversion Rate (Alibaba 2018)


• [Wide & Deep] Wide & Deep Learning for Recommender Systems (Google 2016)


• [xDeepFM] xDeepFM - Combining Explicit and Implicit Feature Interactions for Recommender Systems (USTC 2018)


• [Image CTR] Image Matters - Visually modeling user behaviors using Advanced Model Server (Alibaba 2018)


• [AFM] Attentional Factorization Machines - Learning the Weight of Feature Interactions via Attention Networks (ZJU 2017)


• [DIEN] Deep Interest Evolution Network for Click-Through Rate Prediction (Alibaba 2019)


• [DSSM] Learning Deep Structured Semantic Models for Web Search using Clickthrough Data (UIUC 2013)


• [FNN] Deep Learning over Multi-field Categorical Data (UCL 2016)


• [DeepFM] A Factorization-Machine based Neural Network for CTR Prediction (HIT-Huawei 2017)


• [NFM] Neural Factorization Machines for Sparse Predictive Analytics (NUS 2017)

Exploration and Exploitation

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

Allocation

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