A Fast Algorithm for PAC Combinatorial Pure Exploration
Keywords:Machine Learning (ML)
AbstractWe 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.
How to Cite
Ben-David, N., & Sabato, S. (2022). A Fast Algorithm for PAC Combinatorial Pure Exploration. Proceedings of the AAAI Conference on Artificial Intelligence, 36(6), 6064-6071. https://doi.org/10.1609/aaai.v36i6.20553
AAAI Technical Track on Machine Learning I