中文
相关论文

相关论文: Federated Linear Bandits with Finite Adversarial A…

200 篇论文

Most existing works on federated bandits take it for granted that all clients are altruistic about sharing their data with the server for the collective good whenever needed. Despite their compelling theoretical guarantee on performance and…

机器学习 · 计算机科学 2023-10-24 Zhepei Wei , Chuanhao Li , Haifeng Xu , Hongning Wang

We study a new non-stochastic federated multi-armed bandit problem with multiple agents collaborating via a communication network. The losses of the arms are assigned by an oblivious adversary that specifies the loss of each arm not only…

机器学习 · 统计学 2023-10-24 Jialin Yi , Milan Vojnović

This paper considers the contextual multi-armed bandit (CMAB) problem with fairness and privacy guarantees in a federated environment. We consider merit-based exposure as the desired fair outcome, which provides exposure to each action in…

机器学习 · 计算机科学 2024-02-07 Sambhav Solanki , Shweta Jain , Sujit Gujar

By exploiting the computing power and local data of distributed clients, federated learning (FL) features ubiquitous properties such as reduction of communication overhead and preserving data privacy. In each communication round of FL, the…

信息论 · 计算机科学 2020-07-21 Wenchao Xia , Tony Q. S. Quek , Kun Guo , Wanli Wen , Howard H. Yang , Hongbo Zhu

Despite the significant interest and progress in reinforcement learning (RL) problems with adversarial corruption, current works are either confined to the linear setting or lead to an undesired $\tilde{O}(\sqrt{T}\zeta)$ regret bound,…

机器学习 · 统计学 2024-02-13 Chenlu Ye , Wei Xiong , Quanquan Gu , Tong Zhang

This paper considers contextual bandits with a finite number of arms, where the contexts are independent and identically distributed $d$-dimensional random vectors, and the expected rewards are linear in both the arm parameters and…

机器学习 · 统计学 2025-05-07 Yanglei Song , Meng zhou

Contextual bandits are widely used in Internet services from news recommendation to advertising, and to Web search. Generalized linear models (logistical regression in particular) have demonstrated stronger performance than linear models in…

机器学习 · 计算机科学 2017-06-20 Lihong Li , Yu Lu , Dengyong Zhou

We study how representation learning can improve the efficiency of bandit problems. We study the setting where we play $T$ linear bandits with dimension $d$ concurrently, and these $T$ bandit tasks share a common $k (\ll d)$ dimensional…

机器学习 · 计算机科学 2021-05-06 Jiaqi Yang , Wei Hu , Jason D. Lee , Simon S. Du

Safety is a desirable property that can immensely increase the applicability of learning algorithms in real-world decision-making problems. It is much easier for a company to deploy an algorithm that is safe, i.e., guaranteed to perform at…

机器学习 · 统计学 2017-03-07 Abbas Kazerouni , Mohammad Ghavamzadeh , Yasin Abbasi-Yadkori , Benjamin Van Roy

Recently, there has been extensive study of cooperative multi-agent multi-armed bandits where a set of distributed agents cooperatively play the same multi-armed bandit game. The goal is to develop bandit algorithms with the optimal group…

机器学习 · 计算机科学 2023-08-09 Lin Yang , Xuchuang Wang , Mohammad Hajiesmaili , Lijun Zhang , John C. S. Lui , Don Towsley

This paper studies representation learning for multi-task linear bandits and multi-task episodic RL with linear value function approximation. We first consider the setting where we play $M$ linear bandits with dimension $d$ concurrently,…

机器学习 · 计算机科学 2021-02-09 Jiachen Hu , Xiaoyu Chen , Chi Jin , Lihong Li , Liwei Wang

We study replicable algorithms for stochastic multi-armed bandits (MAB) and linear bandits with UCB (Upper Confidence Bound) based exploration. A bandit algorithm is $\rho$-replicable if two executions using shared internal randomness but…

机器学习 · 计算机科学 2026-04-23 Rohan Deb , Udaya Ghai , Karan Singh , Arindam Banerjee

We study distributed adversarial bandits, where $N$ agents cooperate to minimize the global average loss while observing only their own local losses. We show that the minimax regret for this problem is…

机器学习 · 计算机科学 2026-02-09 Hao Qiu , Mengxiao Zhang , Nicolò Cesa-Bianchi

A general framework of personalized federated multi-armed bandits (PF-MAB) is proposed, which is a new bandit paradigm analogous to the federated learning (FL) framework in supervised learning and enjoys the features of FL with…

机器学习 · 计算机科学 2021-02-26 Chengshuai Shi , Cong Shen , Jing Yang

We prove that two popular linear contextual bandit algorithms, OFUL and Thompson Sampling, can be made efficient using Frequent Directions, a deterministic online sketching technique. More precisely, we show that a sketch of size $m$ allows…

机器学习 · 计算机科学 2022-03-22 Ilja Kuzborskij , Leonardo Cella , Nicolò Cesa-Bianchi

This paper investigates the robustness of causal bandits (CBs) in the face of temporal model fluctuations. This setting deviates from the existing literature's widely-adopted assumption of constant causal models. The focus is on causal…

机器学习 · 统计学 2024-05-14 Zirui Yan , Arpan Mukherjee , Burak Varıcı , Ali Tajer

This study investigates the problem of $K$-armed linear contextual bandits, an instance of the multi-armed bandit problem, under an adversarial corruption. At each round, a decision-maker observes an independent and identically distributed…

机器学习 · 计算机科学 2023-12-29 Masahiro Kato , Shinji Ito

We study a variant of the stochastic linear bandit problem wherein we optimize a linear objective function but rewards are accrued only orthogonal to an unknown subspace (which we interpret as a \textit{protected space}) given only…

机器学习 · 计算机科学 2021-03-03 Advait Parulekar , Soumya Basu , Aditya Gopalan , Karthikeyan Shanmugam , Sanjay Shakkottai

In this paper, we study the problem of stochastic linear bandits with finite action sets. Most of existing work assume the payoffs are bounded or sub-Gaussian, which may be violated in some scenarios such as financial markets. To settle…

机器学习 · 计算机科学 2020-04-29 Bo Xue , Guanghui Wang , Yimu Wang , Lijun Zhang

We introduce the first best-of-both-worlds algorithm for contextual combinatorial semi-bandits that simultaneously guarantees $\widetilde{\mathcal{O}}(\sqrt{T})$ regret in the adversarial regime and $\widetilde{\mathcal{O}}(\ln T)$ regret…

机器学习 · 统计学 2026-03-27 Mengmeng Li , Philipp J. Schneider , Jelisaveta Aleksić , Daniel Kuhn