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. 2405.17968
14
0

Matroid Semi-Bandits in Sublinear Time

28 May 2024
Ruo-Chun Tzeng
Naoto Ohsaka
Kaito Ariu
ArXivPDFHTML
Abstract

We study the matroid semi-bandits problem, where at each round the learner plays a subset of KKK arms from a feasible set, and the goal is to maximize the expected cumulative linear rewards. Existing algorithms have per-round time complexity at least Ω(K)\Omega(K)Ω(K), which becomes expensive when KKK is large. To address this computational issue, we propose FasterCUCB whose sampling rule takes time sublinear in KKK for common classes of matroids: O(D polylog(K) polylog(T))O(D\text{ polylog}(K)\text{ polylog}(T))O(D polylog(K) polylog(T)) for uniform matroids, partition matroids, and graphical matroids, and O(DK polylog(T))O(D\sqrt{K}\text{ polylog}(T))O(DK​ polylog(T)) for transversal matroids. Here, DDD is the maximum number of elements in any feasible subset of arms, and TTT is the horizon. Our technique is based on dynamic maintenance of an approximate maximum-weight basis over inner-product weights. Although the introduction of an approximate maximum-weight basis presents a challenge in regret analysis, we can still guarantee an upper bound on regret as tight as CUCB in the sense that it matches the gap-dependent lower bound by Kveton et al. (2014a) asymptotically.

View on arXiv
Comments on this paper