conference-paper Open access

A Fast Algorithm for PAC Combinatorial Pure Exploration

  • Proceedings of the AAAI Conference on Artificial Intelligence
  • Association for the Advancement of Artificial Intelligence
Research footprint

At a glance

Citations
1
References
20
Comments
0
Paper overview

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.

Record transparency

Publication details

DOI
10.1609/aaai.v36i6.20553
OpenAlex
W4283814085
Document type
conference-paper
Language
EN
Source
Proceedings of the AAAI Conference on Artificial Intelligence
Last metadata update
Community

Comments

Log in to join the discussion.

  1. No comments yet. Start the discussion.