.png){kind=icon}
返回
Corruption-tolerant bandit learning
.png){kind=icon}
OA
AI
DOI：10.1007/s10994-018-5758-5.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
We present algorithms for solving multi-armed and linear-contextual bandit tasks in the face of adversarial corruptions in the arm responses. Traditional algorithms for solving these problems assume that nothing but mild, e.g., i.i.d. sub-Gaussian, noise disrupts an otherwise clean estimate of the utility of the arm. This assumption and the resulting approaches can fail catastrophically if there is an observant adversary that corrupts even a small fraction of the responses generated when arms are pulled. To rectify this, we propose algorithms that use recent advances in robust statistical estimation to perform arm selection in polynomial time. Our algorithms are easy to implement and vastly outperform several existing UCB and EXP-style algorithms for stochastic and adversarial multi-armed and linear-contextual bandit problems in wide variety of experimental settings. Our algorithms enjoy minimax-optimal regret bounds, as well as can tolerate an adversary that is allowed to corrupt upto a universally constant fraction of the arms pulled by the algorithm.
Keyword:
Robust learning
Online learning
Bandit algorithms
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
2.9
论文数:
2.7K
被引数:
3.4W
机构
引用论文
.png){kind=icon}
Mobile markerless augmented reality and its application in forensic medicine移动无标记增强现实技术及其在法医学中的应用
PREAI
分享收藏
Bistability of alpha‐motoneurones in the decerebrate cat and in the acute spinal cat after intravenous 5‐hydroxytryptophan.静脉注射5-羟色氨酸后，去脑猫和急性脊髓猫中 α-运动神经元的双稳态。OAAI
OAAI分享收藏Vasodilatory effects of adenosine A2 receptor agonists CGS 21680 and CGS 22492 in human vasculature
PREAI
分享收藏
查看更多内容