Home
Scholarly Works
A Fast Algorithm for PAC Combinatorial Pure...
Conference

A Fast Algorithm for PAC Combinatorial Pure Exploration

Abstract

We consider the problem of Combinatorial Pure Exploration (CPE), which deals with finding a combinatorial set of arms with a high reward, when the rewards of individual arms are unknown in advance and must be estimated using arm pulls. Previous algorithms for this problem, while obtaining sample complexity reductions in many cases, are highly computationally intensive, thus making them impractical even for mildly large problems. In this work, we propose a new CPE algorithm in the PAC setting, which is computationally light weight, and so can easily be applied to problems with tens of thousands of arms. This is achieved since the proposed algorithm requires a very small number of combinatorial oracle calls. The algorithm is based on successive acceptance of arms, along with elimination which is based on the combinatorial structure of the problem. We provide sample complexity guarantees for our algorithm, and demonstrate in experiments its usefulness on large problems, whereas previous algorithms are impractical to run on problems of even a few dozen arms. The code is provided at https://github.com/noabdavid/csale. The full version of this paper is available at https://arxiv.org/abs/2112.04197.

Authors

Ben-David N; Sabato S

Volume

36

Pagination

pp. 6064-6071

Publisher

Association for the Advancement of Artificial Intelligence (AAAI)

Publication Date

June 30, 2022

DOI

10.1609/aaai.v36i6.20553

Conference proceedings

Proceedings of the AAAI Conference on Artificial Intelligence

Issue

6

ISSN

2159-5399

View published work (Non-McMaster Users)