Stochastic Linear Contextual Bandits with Diverse Contexts

被引:0
|
作者
Wu, Weiqiang [1 ]
Yang, Jing [2 ]
Shen, Cong [3 ]
机构
[1] London Stock Exchange, London, England
[2] Penn State Univ, University Pk, PA 16802 USA
[3] Univ Virginia, Charlottesville, VA 22903 USA
基金
美国国家科学基金会;
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
In this paper, we investigate the impact of context diversity on stochastic linear contextual bandits. As opposed to the previous view that contexts lead to more difficult bandit learning, we show that when the contexts are sufficiently diverse, the learner is able to utilize the information obtained during exploitation to shorten the exploration process, thus achieving reduced regret. We design the LinUCB-d algorithm, and propose a novel approach to analyze its regret performance. The main theoretical result is that under the diverse context assumption, the cumulative expected regret of LinUCB-d is bounded by a constant. As a by-product, our results improve the previous understanding of LinUCB and strengthen its performance guarantee.
引用
收藏
页数:9
相关论文
共 50 条
  • [1] Contexts can be Cheap: Solving Stochastic Contextual Bandits with Linear Bandit Algorithms
    Hanna, Osama A.
    Yang, Lin F.
    Fragouli, Christina
    [J]. THIRTY SIXTH ANNUAL CONFERENCE ON LEARNING THEORY, VOL 195, 2023, 195
  • [2] Stochastic Conservative Contextual Linear Bandits
    Lin, Jiabin
    Lee, Xian Yeow
    Jubery, Talukder
    Moothedath, Shana
    Sarkar, Soumik
    Ganapathysubramanian, Baskar
    [J]. 2022 IEEE 61ST CONFERENCE ON DECISION AND CONTROL (CDC), 2022, : 7321 - 7326
  • [3] Design of Experiments for Stochastic Contextual Linear Bandits
    Zanette, Andrea
    Dong, Kefan
    Lee, Jonathan
    Brunskill, Emma
    [J]. ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 34 (NEURIPS 2021), 2021, 34
  • [4] Learning in Generalized Linear Contextual Bandits with Stochastic Delays
    Zhou, Zhengyuan
    Xu, Renyuan
    Blanchet, Jose
    [J]. ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 32 (NIPS 2019), 2019, 32
  • [5] Stochastic Contextual Dueling Bandits under Linear Stochastic Transitivity Models
    Bengs, Viktor
    Saha, Aadirupa
    Huellermeier, Eyke
    [J]. INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 162, 2022,
  • [6] Robust Stochastic Linear Contextual Bandits Under Adversarial Attacks
    Ding, Qin
    Hsieh, Cho-Jui
    Sharpnack, James
    [J]. INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND STATISTICS, VOL 151, 2022, 151
  • [7] Nonparametric Stochastic Contextual Bandits
    Guan, Melody Y.
    Jiang, Heinrich
    [J]. THIRTY-SECOND AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTIETH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE / EIGHTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2018, : 3119 - 3125
  • [8] Contextual Bandits with Stochastic Experts
    Sen, Rajat
    Shanmugam, Karthikeyan
    Shakkottai, Sanjay
    [J]. INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND STATISTICS, VOL 84, 2018, 84
  • [9] Conservative Contextual Linear Bandits
    Kazerouni, Abbas
    Ghavamzadeh, Mohammad
    Abbasi-Yadkori, Yasin
    Van Roy, Benjamin
    [J]. ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 30 (NIPS 2017), 2017, 30
  • [10] Balanced Linear Contextual Bandits
    Dimakopoulou, Maria
    Zhou, Zhengyuan
    Athey, Susan
    Imbens, Guido
    [J]. THIRTY-THIRD AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTY-FIRST INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE / NINTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2019, : 3445 - 3453