A Fast Algorithm for PAC Combinatorial Pure Exploration
Noa Ben-David, Sivan Sabato
摘要
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.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了最后一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
相关 Paper
- Thompson Sampling for Real-Valued Combinatorial Pure Exploration of Multi-Armed BanditShintaro Nakamura, Masashi SugiyamaAAAI 2024 · 被引用 7 次
- Thompson Sampling for (Combinatorial) Pure ExplorationSiwei Wang, Jun ZhuICML 2022 · 被引用 8 次
- Combinatorial Pure Exploration with Full-Bandit or Partial Linear FeedbackYihan Du, Yuko Kuroki, Wei ChenAAAI 2021 · 被引用 23 次
- Combinatorial Pure Exploration for Dueling BanditWei Chen, Yihan Du, Longbo Huang, Haoyu ZhaoICML 2020 · 被引用 14 次
- Combinatorial Pure Exploration with Bottleneck Reward FunctionYihan Du, Yuko Kuroki, Wei ChenNeurIPS 2021 · 被引用 6 次
