Learning from Distributed Users in Contextual Linear Bandits Without Sharing the Context

Osama Hanna, Lin Yang, Christina Fragouli

Keywords: bandits, contextual bandits, linear bandits, distributed contextual bandits, bandits with communication constraints

Abstract: Contextual linear bandits is a rich and theoretically important model that has many practical applications. Recently, this setup gained a lot of interest in applications over wireless where communication constraints can be a performance bottleneck, especially when the contexts come from a large $d$-dimensional space. In this paper, we consider the distributed contextual linear bandit learning problem, where the agents who observe the contexts and take actions are geographically separated from the learner who performs the learning while not seeing the contexts. We assume that contexts are generated from a distribution and propose a method that uses $\approx 5d$ bits per context for the case of unknown context distribution and $0$ bits per context if the context distribution is known, while achieving nearly the same regret bound as if the contexts were directly observable. The former bound improves upon existing bounds by a $\log(T)$ factor, where $T$ is the length of the horizon, while the latter achieves information theoretical tightness.

TL;DR: We propose a method to compress the context using $\approx 5d$ bits per context if the context distribution is unknown and $0$ bits per context if the context distribution is known, while achieving optimal regret.