DeepAI AI Chat
Log In Sign Up

Communication Efficient Distributed Learning for Kernelized Contextual Bandits

by   Chuanhao Li, et al.

We tackle the communication efficiency challenge of learning kernelized contextual bandits in a distributed setting. Despite the recent advances in communication-efficient distributed bandit learning, existing solutions are restricted to simple models like multi-armed bandits and linear bandits, which hamper their practical utility. In this paper, instead of assuming the existence of a linear reward mapping from the features to the expected rewards, we consider non-linear reward mappings, by letting agents collaboratively search in a reproducing kernel Hilbert space (RKHS). This introduces significant challenges in communication efficiency as distributed kernel learning requires the transfer of raw data, leading to a communication cost that grows linearly w.r.t. time horizon T. We addresses this issue by equipping all agents to communicate via a common Nyström embedding that gets updated adaptively as more data points are collected. We rigorously proved that our algorithm can attain sub-linear rate in both regret and communication cost.


page 1

page 2

page 3

page 4


Distributed Bandit Learning: How Much Communication is Needed to Achieve (Near) Optimal Regret

We study the communication complexity of distributed multi-armed bandits...

Communication Efficient Federated Learning for Generalized Linear Bandits

Contextual bandit algorithms have been recently studied under the federa...

A Simple and Provably Efficient Algorithm for Asynchronous Federated Contextual Linear Bandits

We study federated contextual linear bandits, where M agents cooperate w...

Distributed Contextual Linear Bandits with Minimax Optimal Communication Cost

We study distributed contextual linear bandits with stochastic contexts,...

Remote Contextual Bandits

We consider a remote contextual multi-armed bandit (CMAB) problem, in wh...

Efficient Kernel UCB for Contextual Bandits

In this paper, we tackle the computational efficiency of kernelized UCB ...

Online Fair Revenue Maximizing Cake Division with Non-Contiguous Pieces in Adversarial Bandits

The classic cake-cutting problem provides a model for addressing the fai...