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. 2202.10066
16
21

Multi-task Representation Learning with Stochastic Linear Bandits

21 February 2022
Leonardo Cella
Karim Lounici
Grégoire Pacreau
Massimiliano Pontil
ArXivPDFHTML
Abstract

We study the problem of transfer-learning in the setting of stochastic linear bandit tasks. We consider that a low dimensional linear representation is shared across the tasks, and study the benefit of learning this representation in the multi-task learning setting. Following recent results to design stochastic bandit policies, we propose an efficient greedy policy based on trace norm regularization. It implicitly learns a low dimensional representation by encouraging the matrix formed by the task regression vectors to be of low rank. Unlike previous work in the literature, our policy does not need to know the rank of the underlying matrix. We derive an upper bound on the multi-task regret of our policy, which is, up to logarithmic factors, of order NdT(T+d)r\sqrt{NdT(T+d)r}NdT(T+d)r​, where TTT is the number of tasks, rrr the rank, ddd the number of variables and NNN the number of rounds per task. We show the benefit of our strategy compared to the baseline TdNTd\sqrt{N}TdN​ obtained by solving each task independently. We also provide a lower bound to the multi-task regret. Finally, we corroborate our theoretical findings with preliminary experiments on synthetic data.

View on arXiv
Comments on this paper