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. 2010.12642
86
32

Instance-Wise Minimax-Optimal Algorithms for Logistic Bandits

23 October 2020
Marc Abeille
Louis Faury
Clément Calauzènes
ArXivPDFHTML
Abstract

Logistic Bandits have recently attracted substantial attention, by providing an uncluttered yet challenging framework for understanding the impact of non-linearity in parametrized bandits. It was shown by Faury et al. (2020) that the learning-theoretic difficulties of Logistic Bandits can be embodied by a large (sometimes prohibitively) problem-dependent constant κ\kappaκ, characterizing the magnitude of the reward's non-linearity. In this paper we introduce a novel algorithm for which we provide a refined analysis. This allows for a better characterization of the effect of non-linearity and yields improved problem-dependent guarantees. In most favorable cases this leads to a regret upper-bound scaling as O~(dT/κ)\tilde{\mathcal{O}}(d\sqrt{T/\kappa})O~(dT/κ​), which dramatically improves over the O~(dT+κ)\tilde{\mathcal{O}}(d\sqrt{T}+\kappa)O~(dT​+κ) state-of-the-art guarantees. We prove that this rate is minimax-optimal by deriving a Ω(dT/κ)\Omega(d\sqrt{T/\kappa})Ω(dT/κ​) problem-dependent lower-bound. Our analysis identifies two regimes (permanent and transitory) of the regret, which ultimately re-conciliates Faury et al. (2020) with the Bayesian approach of Dong et al. (2019). In contrast to previous works, we find that in the permanent regime non-linearity can dramatically ease the exploration-exploitation trade-off. While it also impacts the length of the transitory phase in a problem-dependent fashion, we show that this impact is mild in most reasonable configurations.

View on arXiv
Comments on this paper