DeepAI AI Chat
Log In Sign Up

Communication Efficient Distributed Learning for Kernelized Contextual Bandits

06/10/2022
by   Chuanhao Li, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

04/12/2019

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

We study the communication complexity of distributed multi-armed bandits...
02/02/2022

Communication Efficient Federated Learning for Generalized Linear Bandits

Contextual bandit algorithms have been recently studied under the federa...
07/07/2022

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

We study federated contextual linear bandits, where M agents cooperate w...
05/26/2022

Distributed Contextual Linear Bandits with Minimax Optimal Communication Cost

We study distributed contextual linear bandits with stochastic contexts,...
02/10/2022

Remote Contextual Bandits

We consider a remote contextual multi-armed bandit (CMAB) problem, in wh...
02/11/2022

Efficient Kernel UCB for Contextual Bandits

In this paper, we tackle the computational efficiency of kernelized UCB ...
11/29/2021

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...