Bandits and Experts in Metric Spaces

Author:

Kleinberg Robert1,Slivkins Aleksandrs2,Upfal Eli3

Affiliation:

1. Computer Science Department, Cornell University, Ithaca, NY, USA

2. Microsoft Research NYC, New York, NY, USA USA

3. Computer Science Department, Brown University, Providence, RI, USA

Abstract

In a multi-armed bandit problem, an online algorithm chooses from a set of strategies in a sequence of trials to maximize the total payoff of the chosen strategies. While the performance of bandit algorithms with a small finite strategy set is well understood, bandit problems with large strategy sets are still a topic of active investigation, motivated by practical applications, such as online auctions and web advertisement. The goal of such research is to identify broad and natural classes of strategy sets and payoff functions that enable the design of efficient solutions. In this work, we study a general setting for the multi-armed bandit problem, in which the strategies form a metric space, and the payoff function satisfies a Lipschitz condition with respect to the metric. We refer to this problem as the Lipschitz MAB problem . We present a solution for the multi-armed bandit problem in this setting. That is, for every metric space, we define an isometry invariant that bounds from below the performance of Lipschitz MAB algorithms for this metric space, and we present an algorithm that comes arbitrarily close to meeting this bound. Furthermore, our technique gives even better results for benign payoff functions. We also address the full-feedback (“best expert”) version of the problem, where after every round the payoffs from all arms are revealed.

Funder

NSF

ONR

Publisher

Association for Computing Machinery (ACM)

Subject

Artificial Intelligence,Hardware and Architecture,Information Systems,Control and Systems Engineering,Software

Cited by 18 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. The Power of Age-based Reward in Fresh Information Acquisition;IEEE INFOCOM 2023 - IEEE Conference on Computer Communications;2023-05-17

2. An Online Inference-Aided Incentive Framework for Information Elicitation Without Verification;IEEE Journal on Selected Areas in Communications;2023-04

3. Starlet: Network defense resource allocation with multi-armed bandits for cloud-edge crowd sensing in IoT;Digital Communications and Networks;2023-03

4. Doubly High-Dimensional Contextual Bandits: An Interpretable Model for Joint Assortment-Pricing;SSRN Electronic Journal;2023

5. Invariant Lipschitz Bandits: A Side Observation Approach;Machine Learning and Knowledge Discovery in Databases: Research Track;2023

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3