Provably Efficient Multi-Task Meta Bandit Learning via Shared Representations

Jiabin Lin, Shana Moothedath

Keywords: Meta learning, Multi-task learning, Linear bandits, Low dimensional learning, Representation learning

TL;DR: We study meta-learning in linear bandits and provide provably fast, sample-efficient algorithms to learn a common set of features from multiple related bandit tasks and to transfer this knowledge to new, unseen bandit tasks.

Abstract: Learning-to-learn or meta-learning focuses on developing algorithms that leverage prior experience to quickly acquire new skills or adapt to novel environments. A crucial component of meta-learning is representation learning, which aims to construct data representations capable of transferring knowledge across multiple tasks—a critical advantage in data-scarce settings. We study how representation learning can improve the efficiency of bandit problems. We consider $T$ $d$-dimensional linear bandits that share a common low-dimensional linear representation. We provide provably fast, sample-efficient algorithms to address the two key problems in meta-learning: (1) learning a common set of features from multiple related bandit tasks and (2) transferring this knowledge to new, unseen bandit tasks. We validated the theoretical results through numerical experiments using real-world and synthetic datasets, comparing them against benchmark algorithms.

Primary Area: General machine learning (supervised, unsupervised, online, active, etc.)

Submission Number: 13233