Motivated by practical needs such as large-scale learning, we study the impact of adaptivity
constraints to linear contextual bandits, a central problem in online learning and decision …

This paper introduces a general multi-agent bandit model in which each agent is facing a
finite set of arms and may communicate with other agents through a central controller in …

We tackle the communication efficiency challenge of learning kernelized contextual bandits
in a distributed setting. Despite the recent advances in communication-efficient distributed …

Regret minimization in streaming multi-armed bandits (MABs) has been studied extensively,
and recent work has shown that algorithms with $ o (K) $ memory have to incur $\Omega …

Multi-distribution learning generalizes the classic PAC learning to handle data coming from
multiple distributions. Given a set of $ k $ data distributions and a hypothesis class of VC …

We study a federated variant of the best-arm identification problem in stochastic multi-armed
bandits: a set of clients, each of whom can sample only a subset of the arms, collaborate via …

Most existing works on federated bandits take it for granted that all clients are altruistic about
sharing their data with the server for the collective good whenever needed. Despite their …

This paper studies two variants of the best arm identification (BAI) problem under the
streaming model, where we have a stream of n arms with reward distributions supported on …

We consider distributed linear bandits where $ M $ agents learn collaboratively to minimize
the overall cumulative regret incurred by all agents. Information exchange is facilitated by a …

We consider the following problem in this paper: given a set of n distributions, find the top-m
ones with the largest means. This problem is also called top-m arm identifications in the …