Transfer Learning in Bandits with Latent Continuity

by   Hyejin Park, et al.

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.


page 1

page 2

page 3

page 4


Lifting the Information Ratio: An Information-Theoretic Analysis of Thompson Sampling for Contextual Bandits

We study the Bayesian regret of the renowned Thompson Sampling algorithm...

Optimal Learning for Structured Bandits

We study structured multi-armed bandits, which is the problem of online ...

Bounded Regret for Finitely Parameterized Multi-Armed Bandits

We consider the problem of finitely parameterized multi-armed bandits wh...

Hypothesis Transfer in Bandits by Weighted Models

We consider the problem of contextual multi-armed bandits in the setting...

Transfer Learning for Contextual Multi-armed Bandits

Motivated by a range of applications, we study in this paper the problem...

Warm Starting Bandits with Side Information from Confounded Data

We study a variant of the multi-armed bandit problem where side informat...

Please sign up or login with your details

Forgot password? Click here to reset