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. 2003.10550
25
1
v1v2v3 (latest)

Sublinear Regret and Belief Complexity in Gaussian Process Bandits via Information Thresholding

23 March 2020
Amrit Singh Bedi
Dheeraj Peddireddy
Vaneet Aggarwal
Brian M. Sadler
ArXiv (abs)PDFHTML
Abstract

Bayesian optimization is a framework for global search via maximum a posteriori updates rather than simulated annealing, and has gained prominence for decision-making under uncertainty. In this work, we cast Bayesian optimization as a multi-armed bandit problem, where the payoff function is sampled from a Gaussian process (GP). Further, we focus on action selections via upper confidence bound (UCB) or expected improvement (EI) due to their prevalent use in practice. Prior works using GPs for bandits cannot allow the iteration horizon TTT to be large, as the complexity of computing the posterior parameters scales cubically with the number of past observations. To circumvent this computational burden, we propose a simple statistical test: only incorporate an action into the GP posterior when its conditional entropy exceeds an ϵ\epsilonϵ threshold. Doing so permits us to derive sublinear regret bounds of GP bandit algorithms up to factors depending on the compression parameter ϵ\epsilonϵ for both discrete and continuous action sets. Moreover, the complexity of the GP posterior remains provably finite and depends on the Shannon capacity of the observation space. Experimentally, we observe state of the art accuracy and complexity tradeoffs for GP bandit algorithms applied to global optimization, suggesting the merits of compressed GPs in bandit settings.

View on arXiv
Comments on this paper