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. 2205.15100
13
5

Meta Representation Learning with Contextual Linear Bandits

30 May 2022
Leonardo Cella
Karim Lounici
Massimiliano Pontil
ArXivPDFHTML
Abstract

Meta-learning seeks to build algorithms that rapidly learn how to solve new learning problems based on previous experience. In this paper we investigate meta-learning in the setting of stochastic linear bandit tasks. We assume that the tasks share a low dimensional representation, which has been partially acquired from previous learning tasks. We aim to leverage this information in order to learn a new downstream bandit task, which shares the same representation. Our principal contribution is to show that if the learned representation estimates well the unknown one, then the downstream task can be efficiently learned by a greedy policy that we propose in this work. We derive an upper bound on the regret of this policy, which is, up to logarithmic factors, of order rN(1∨d/T)r\sqrt{N}(1\vee \sqrt{d/T})rN​(1∨d/T​), where NNN is the horizon of the downstream task, TTT is the number of training tasks, ddd the ambient dimension and r≪dr \ll dr≪d the dimension of the representation. We highlight that our strategy does not need to know rrr. We note that if T>dT> dT>d our bound achieves the same rate of optimal minimax bandit algorithms using the true underlying representation. Our analysis is inspired and builds in part upon previous work on meta-learning in the i.i.d. full information setting \citep{tripuraneni2021provable,boursier2022trace}. As a separate contribution we show how to relax certain assumptions in those works, thereby improving their representation learning and risk analysis.

View on arXiv
Comments on this paper