ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 1711.08018
38
8

Disagreement-Based Combinatorial Pure Exploration: Sample Complexity Bounds and an Efficient Algorithm

21 November 2017
Tongyi Cao
A. Krishnamurthy
ArXivPDFHTML
Abstract

We design new algorithms for the combinatorial pure exploration problem in the multi-arm bandit framework. In this problem, we are given KKK distributions and a collection of subsets V⊂2[K]\mathcal{V} \subset 2^{[K]}V⊂2[K] of these distributions, and we would like to find the subset v∈Vv \in \mathcal{V}v∈V that has largest mean, while collecting, in a sequential fashion, as few samples from the distributions as possible. In both the fixed budget and fixed confidence settings, our algorithms achieve new sample-complexity bounds that provide polynomial improvements on previous results in some settings. Via an information-theoretic lower bound, we show that no approach based on uniform sampling can improve on ours in any regime, yielding the first interactive algorithms for this problem with this basic property. Computationally, we show how to efficiently implement our fixed confidence algorithm whenever V\mathcal{V}V supports efficient linear optimization. Our results involve precise concentration-of-measure arguments and a new algorithm for linear programming with exponentially many constraints.

View on arXiv
Comments on this paper