|
在线实验中的收缩率估计
Shrinkage Estimators in Online Experiments |
|
| |
| 课程网址: |
http://videolectures.net/kdd2019_dimmery_bakshy_sekhon/
|
| 主讲教师: |
Drew Dimmery
|
| 开课单位: |
脸书公司
|
| 开课时间: |
2020-03-02
|
| 课程语种: |
英语
|
| 中文简介: |
我们开发和分析经验贝叶斯斯坦类型估计器，用于大规模在线实验中的因果效应估计。尽管通常认为在线实验以其大样本量而著称，但我们关注的是治疗组的多样性。典型的分析方法是使用均值上的简单差异（可能进行协变量调整），就好像所有治疗组都是独立的一样。在这项工作中，我们针对此设置开发了一致的，小的偏差，收缩率估算器。除了获得较低的均方误差外，这些估算器还保留了重要的常客属性，例如在最合理的情况下的覆盖率。现代的循序渐进的实验和优化方法（例如多武装匪徒优化）（治疗分配随时间推移而适应先前的反应）得益于我们的收缩率估算器。在经验贝叶斯方法下的勘探将更有效地集中在近乎最优的武器上，从而改善了在不确定条件下做出的最终决策。我们通过检查2017年4月至6月在Facebook上进行的十七次常规实验来证明这些特性。
|
| 课程简介: |
We develop and analyze empirical Bayes Stein-type estimators for use in the estimation of causal effects in large-scale online experiments. While online experiments are generally thought to be distinguished by their large sample size, we focus on the multiplicity of treatment groups. The typical analysis practice is to use simple differences-in-means (perhaps with covariate adjustment) as if all treatment arms were independent. In this work we develop consistent, small bias, shrinkage estimators for this setting. In addition to achieving lower mean squared error these estimators retain important frequentist properties such as coverage under most reasonable scenarios. Modern sequential methods of experimentation and optimization such as multi-armed bandit optimization (where treatment allocations adapt over time to prior responses) benefit from the use of our shrinkage estimators. Exploration under empirical Bayes focuses more efficiently on near-optimal arms, improving the resulting decisions made under uncertainty. We demonstrate these properties by examining seventeen routine experiments conducted on Facebook from April to June 2017.
|
| 关 键 词: |
在线实验; 收缩率; 覆盖率
|
| 课程来源: |
视频讲座网
|
| 数据采集: |
2020-03-24：zhouxj
|
| 最后编审: |
2020-05-25：cxin
|
| 阅读次数: |
61
|
|
图 书 馆