Transfer Learning in Bandits with Latent Continuity

TL;DR

This paper introduces a transfer learning framework for structured stochastic bandits that estimates the latent Lipschitz constant from prior tasks, enabling near-optimal regret bounds without prior structural knowledge.

Contribution

It proposes a novel method to accurately estimate the Lipschitz constant from previous tasks and leverages it for improved regret bounds in new tasks, matching theoretical limits.

Findings

Estimator's sample complexity matches information-theoretic limits.

Regret bounds are close to oracle with full Lipschitz knowledge.

Numerical results outperform baseline methods.

Abstract

Structured stochastic multi-armed bandits provide accelerated regret rates over the standard unstructured bandit problems. Most structured bandits, however, assume the knowledge of the structural parameter such as Lipschitz continuity, which is often not available. To cope with the latent structural parameter, we consider a transfer learning setting in which an agent must learn to transfer the structural information from the prior tasks to the next task, which is inspired by practical problems such as rate adaptation in wireless link. We propose a novel framework to provably and accurately estimate the Lipschitz constant based on previous tasks and fully exploit it for the new task at hand. We analyze the efficiency of the proposed framework in two folds: (i) the sample complexity of our estimator matches with the information-theoretic fundamental limit; and (ii) our regret bound on the new task is close to that of the oracle algorithm with the full knowledge of the Lipschitz constant under mild assumptions. Our analysis reveals a set of useful insights on transfer learning for latent Lipschitzconstants such as the fundamental challenge a learner faces. Our numerical evaluations confirm our theoretical findings and show the superiority of the proposed framework compared to baselines.