Year: 2025
Type: conference-paper
Abstract: Best arm identification (BAI) is a key problem in stochastic multi-armed bandits, where K arms each has an associated reward distribution, and the objective is to minimize the number of queries needed to identify the best arm with high confidence. In this paper, we explore BAI using quantum oracles. For the case where each query probes only one arm (m=1), we devise a quantum algorithm with a query complexity upper bound of O((K/Delta)log(1/delta)), where delta is the confidence parameter and Delta is the reward gap between best and second best arms. This improves on the classical bound by a factor of 1/Delta. For the general case where a single query can probe m arms (1
Language: English
Field: Decision Sciences
Domain: Social Sciences
Open Access status: diamond
Awards: Collaborative Research: CNS Core: Small: Dynamic Pricing and Procurement for Distributed Networked Platforms, CAREER: A Robust and Data-driven Design for Carbon-intelligent Distributed Systems, Collaborative Research: CNS Core: Medium: Design and Analysis of Quantum Networks for Entanglement Distribution, G6671297155, Collaborative Research: CNS Core: Medium: Dynamic Data-driven Systems - Theory and Applications, G7444832178, NSF Engineering Research Center for Quantum Networks (CQN), National Science Foundation Expeditions in Computing for Computational Decarbonization of Societal Infrastructures at Mesoscales, Collaborative Research: CPS Medium: Enabling DER Integration via Redesign of Information Flows
OpenAlex ID: W4409363133