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. 2201.09910
13
13

Learning Neural Contextual Bandits Through Perturbed Rewards

24 January 2022
Yiling Jia
Weitong Zhang
Dongruo Zhou
Quanquan Gu
Hongning Wang
ArXivPDFHTML
Abstract

Thanks to the power of representation learning, neural contextual bandit algorithms demonstrate remarkable performance improvement against their classical counterparts. But because their exploration has to be performed in the entire neural network parameter space to obtain nearly optimal regret, the resulting computational cost is prohibitively high. We perturb the rewards when updating the neural network to eliminate the need of explicit exploration and the corresponding computational overhead. We prove that a O~(d~T)\tilde{O}(\tilde{d}\sqrt{T})O~(d~T​) regret upper bound is still achievable under standard regularity conditions, where TTT is the number of rounds of interactions and d~\tilde{d}d~ is the effective dimension of a neural tangent kernel matrix. Extensive comparisons with several benchmark contextual bandit algorithms, including two recent neural contextual bandit models, demonstrate the effectiveness and computational efficiency of our proposed neural bandit algorithm.

View on arXiv
Comments on this paper