Robust Stochastic Linear Contextual Bandits Under Adversarial Attacks

被引:0
作者
Ding, Qin [1 ]
Hsieh, Cho-Jui [2 ]
Sharpnack, James [3 ]
机构
[1] Univ Calif Davis, Dept Stat, Davis, CA 95616 USA
[2] Univ Calif Los Angeles, Dept Comp Sci, Los Angeles, CA 90024 USA
[3] Amazon, Berkeley, CA USA
来源
INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND STATISTICS, VOL 151 | 2022年 / 151卷
关键词
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Stochastic linear contextual bandit algorithms have substantial applications in practice, such as recommender systems, online advertising, clinical trials, etc. Recent works show that optimal bandit algorithms are vulnerable to adversarial attacks and can fail completely in the presence of attacks. Existing robust bandit algorithms only work for the non-contextual setting under the attack of rewards and cannot improve the robustness in the general and popular contextual bandit environment. In addition, none of the existing methods can defend against attacked context. In this work, we provide the first robust bandit algorithm for stochastic linear contextual bandit setting under a fully adaptive and omniscient attack with sub-linear regret. Our algorithm not only works under the attack of rewards, but also under attacked context. Moreover, it does not need any information about the attack budget or the particular form of the attack. We provide theoretical guarantees for our proposed algorithm and show by experiments that our proposed algorithm improves the robustness against various kinds of popular attacks.
引用
收藏
页数:13
相关论文
共 22 条
[1]  
Abbasi- Yadkori Yasin, 2011, P ADV NEUR INF PROC, V11, P2312
[2]  
Agrawal S., 2013, INT C MACHINE LEARNI, V28, P127, DOI DOI 10.5555/3042817.3043073
[3]  
Auer P, 2003, SIAM J COMPUT, V32, P48, DOI 10.1137/S0097539701398375
[4]  
Bogunovic I, 2021, PR MACH LEARN RES, V130
[5]  
Bogunovic I, 2020, PR MACH LEARN RES, V108, P1071
[6]  
Cheung WC, 2019, PR MACH LEARN RES, V89
[7]  
Ding Q, 2021, PR MACH LEARN RES, V130
[8]  
Garcelon E, 2020, ADV NEUR IN, V33
[9]  
Gupta A, 2019, PR MACH LEARN RES, V99
[10]  
Jun KS, 2018, ADV NEUR IN, V31