(Private) Kernelized Bandits with Distributed Biased Feedback
(Private) Kernelized Bandits with Distributed Biased Feedback
复制标题
具有分布式偏差反馈的(私人)内核化强盗
DOI:
10.1145/3579318
复制
发表时间:
2023
期刊:
影响因子:
--
通讯作者:
Ji, Bo
中科院分区:
文献类型:
--
作者:
Li, Fengjiao;Zhou, Xingyu;Ji, Bo
In this paper, we study kernelized bandits with distributed biased feedback. This problem is motivated by several real-world applications (such as dynamic pricing, cellular network configuration, and policy making), where users from a large population contribute to the reward of the action chosen by a central entity, but it is difficult to collect feedback from all users. Instead, only biased feedback (due to user heterogeneity) from a subset of users may be available. In addition to such partial biased feedback, we are also faced with two practical challenges due to communication cost and computation complexity. To tackle these challenges, we carefully design a new distributed phase-then-batch-based elimination (DPBE) algorithm, which samples users in phases for collecting feedback to reduce the bias and employs maximum variance reduction to select actions in batches within each phase. By properly choosing the phase length, the batch size, and the confidence width used for eliminating suboptimal actions, we show that DPBE achieves a sublinear regret of ~O(T1-α/2 +√γT T), where α ∈ (0,1) is the user-sampling parameter one can tune. Moreover, DPBE can significantly reduce both communication cost and computation complexity in distributed kernelized bandits, compared to some variants of the state-of-the-art algorithms (originally developed for standard kernelized bandits). Furthermore, by incorporating various differential privacy models (including the central, local, and shuffle models), we generalize DPBE to provide privacy guarantees for users participating in the distributed learning process. Finally, we conduct extensive simulations to validate our theoretical results and evaluate the empirical performance.
登录
查看更多内容
DOI:
10.1145/3452296.3472906
发表时间:
2021
期刊:
Proceedings of the 2021 ACM SIGCOMM 2021 Conference
影响因子:
--
作者:
A. Mahimkar;A. Sivakumar;Zihui Ge;Shomik Pathak;Karunasish Biswas
通讯作者:
Karunasish Biswas
DOI:
--
发表时间:
2021
期刊:
Advances in neural information processing systems
影响因子:
--
作者:
Zhu, Yinglun;Zhou, Dongruo;Jiang, Ruoxi;Gu, Quanquan;Willett, Rebecca;Nowak, Robert
通讯作者:
Nowak, Robert
DOI:
--
发表时间:
2021-10
期刊:
ArXiv
影响因子:
--
作者:
Zihan Li;J. Scarlett
通讯作者:
Zihan Li;J. Scarlett
DOI:
10.23919/wiopt56218.2022.9930524
发表时间:
2022-07
期刊:
2022 20th International Symposium on Modeling and Optimization in Mobile, Ad hoc, and Wireless Networks (WiOpt)
影响因子:
--
作者:
Fengjiao Li;Xingyu Zhou;Bo Ji
通讯作者:
Fengjiao Li;Xingyu Zhou;Bo Ji
DOI:
10.48550/arxiv.2203.15589
发表时间:
2022-03
期刊:
ArXiv
影响因子:
--
作者:
Xingyu Zhou;Bo Ji
通讯作者:
Xingyu Zhou;Bo Ji