《强化学习》第二章：多臂老虎机模型本文是《Reinforcement Learning》（by Richard S. Sutton and Andrew G. Barto）第二章Multi-arm Bandits的阅读笔记。Apr 8, 2021Apr 8, 2021
论文笔记：Neural Input Search for Large Scale Recommendation Models论文标题：Neural Input Search for Large Scale Recommendation ModelsApr 4, 2021Apr 4, 2021
论文笔记：推荐系统中的抽样度量指标（KDD 2020最佳研究论文）论文标题：On Sampled Metrics for Item RecommendationApr 3, 2021Apr 3, 2021
【阅读笔记】Youtube 2019年推荐算法论文：推荐下一个视频看什么标题：Recommending what video to watch next: a multitask ranking systemMar 25, 2021Mar 25, 2021
论文笔记：理解Google MMoE模型论文标题：Modeling Task Relationships in Multi-task Learning with Multi-gate Mixture-of-ExpertsMar 23, 2021Mar 23, 2021
PLE模型阅读笔记本文是RecSys2020最佳长论文Progressive Layered Extraction (PLE): A Novel Multi-Task Learning (MTL) Model for Personalized Recommendations的阅读笔记。Mar 21, 2021Mar 21, 2021
技术博客阅读笔记：揭秘Pinterest广告组的深度学习推荐模型实践文章标题：How we use AutoML, Multi-task learning and Multi-tower models for Pinterest AdsFeb 19, 2021Feb 19, 2021
论文阅读笔记：理解Informer模型结构（AAAI 2021 best paper）论文题目：Informer: Beyond Efficient Transformer for Long Sequence Time-Series ForecastingFeb 18, 2021Feb 18, 2021
论文阅读笔记：Behavior-based Popularity Ranking on Amazon Video论文目的：预测video未来的popularity。但对于冷启动的video，因为没有过往的信息，很难进行建模。Feb 14, 20211Feb 14, 20211
