Non-stationary Bandits with Heavy Tail

被引：0
|
作者：
Pan, Weici [1 ]
Liu, Zhenhua [1 ]
机构：
[1] Stony Brook University, United States
来源：
Performance Evaluation Review | 2024年 / 52卷 / 02期
关键词：
Gaussian assumption - Heavy-tailed - Heavy-tails - Multiarmed bandits (MABs) - Nonstationary - Performance - Risk neutrals - Sub-Gaussians;
D O I：
10.1145/3695411.3695424
中图分类号：
学科分类号：
摘要：
In this study, we investigate the performance of multi-armed bandit algorithms in environments characterized by heavytailed and non-stationary reward distributions, a setting that deviates from the conventional risk-neutral and sub- Gaussian assumptions. © 2024 Copyright is held by the owner/author(s).
引用
收藏
页码：33 / 35
相关论文
共 50 条
  • [1] Non-stationary Bandits with Knapsacks
    Liu, Shang
    Jiang, Jiashuo
    Li, Xiaocheng
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 35, NEURIPS 2022, 2022,
  • [2] Unifying Clustered and Non-stationary Bandits
    Li, Chuanhao
    Wu, Qingyun
    Wang, Hongning
    24TH INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND STATISTICS (AISTATS), 2021, 130
  • [3] The problem of the stationary and non-stationary tail
    Volberg, O
    COMPTES RENDUS DE L ACADEMIE DES SCIENCES DE L URSS, 1939, 24 : 657 - 661
  • [4] Cascading Non-Stationary Bandits: Online Learning to Rank in the Non-Stationary Cascade Model
    Li, Chang
    de Rijke, Maarten
    PROCEEDINGS OF THE TWENTY-EIGHTH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, 2019, : 2859 - 2865
  • [5] A Simple Approach for Non-stationary Linear Bandits
    Zhao, Peng
    Zhang, Lijun
    Jiang, Yuan
    Zhou, Zhi-Hua
    INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND STATISTICS, VOL 108, 2020, 108 : 746 - 754
  • [6] Learning Contextual Bandits in a Non-stationary Environment
    Wu, Qingyun
    Iyer, Naveen
    Wang, Hongning
    ACM/SIGIR PROCEEDINGS 2018, 2018, : 495 - 504
  • [7] Weighted Linear Bandits for Non-Stationary Environments
    Russac, Yoan
    Vernade, Claire
    Cappe, Olivier
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 32 (NIPS 2019), 2019, 32
  • [8] Competing Bandits in Non-Stationary Matching Markets
    Ghosh, Avishek
    Sankararaman, Abishek
    Ramchandran, Kannan
    Javidi, Tara
    Mazumdar, Arya
    IEEE TRANSACTIONS ON INFORMATION THEORY, 2024, 70 (04) : 2831 - 2850
  • [9] Weighted Gaussian Process Bandits for Non-stationary Environments
    Deng, Yuntian
    Zhou, Xingyu
    Kim, Baekjin
    Tewari, Ambuj
    Gupta, Abhishek
    Shroff, Ness
    INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND STATISTICS, VOL 151, 2022, 151
  • [10] Stochastic Bandits with Graph Feedback in Non-Stationary Environments
    National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing
    210023, China
    不详
    100102, China
    AAAI Conf. Artif. Intell., AAAI, 1600, (8758-8766): : 8758 - 8766
12345