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. 2007.08584
22
9

Self-Tuning Bandits over Unknown Covariate-Shifts

16 July 2020
Joe Suk
Samory Kpotufe
ArXivPDFHTML
Abstract

Bandits with covariates, a.k.a. contextual bandits, address situations where optimal actions (or arms) at a given time ttt, depend on a context xtx_txt​, e.g., a new patient's medical history, a consumer's past purchases. While it is understood that the distribution of contexts might change over time, e.g., due to seasonalities, or deployment to new environments, the bulk of studies concern the most adversarial such changes, resulting in regret bounds that are often worst-case in nature. Covariate-shift on the other hand has been considered in classification as a middle-ground formalism that can capture mild to relatively severe changes in distributions. We consider nonparametric bandits under such middle-ground scenarios, and derive new regret bounds that tightly capture a continuum of changes in context distribution. Furthermore, we show that these rates can be adaptively attained without knowledge of the time of shift nor the amount of shift.

View on arXiv
Comments on this paper