DeepAI AI Chat
Log In Sign Up

Communication Efficient Federated Learning for Generalized Linear Bandits

02/02/2022
by   Chuanhao Li, et al.
0

Contextual bandit algorithms have been recently studied under the federated learning setting to satisfy the demand of keeping data decentralized and pushing the learning of bandit models to the client side. But limited by the required communication efficiency, existing solutions are restricted to linear models to exploit their closed-form solutions for parameter estimation. Such a restricted model choice greatly hampers these algorithms' practical utility. In this paper, we take the first step to addressing this challenge by studying generalized linear bandit models under a federated learning setting. We propose a communication-efficient solution framework that employs online regression for local update and offline regression for global update. We rigorously proved that, though the setting is more general and challenging, our algorithm can attain sub-linear rate in both regret and communication cost, which is also validated by our extensive empirical evaluations.

READ FULL TEXT

page 1

page 2

page 3

page 4

10/04/2021

Asynchronous Upper Confidence Bound Algorithms for Federated Linear Bandits

Linear contextual bandit is a popular online learning problem. It has be...
02/13/2023

Communication-Efficient Federated Bilevel Optimization with Local and Global Lower Level Problems

Bilevel Optimization has witnessed notable progress recently with new em...
06/10/2022

Communication Efficient Distributed Learning for Kernelized Contextual Bandits

We tackle the communication efficiency challenge of learning kernelized ...
01/28/2021

Federated Multi-Armed Bandits

Federated multi-armed bandits (FMAB) is a new bandit paradigm that paral...
04/04/2022

FedSynth: Gradient Compression via Synthetic Data in Federated Learning

Model compression is important in federated learning (FL) with large mod...
07/16/2022

Kernel-based Federated Learning with Personalization

We consider federated learning with personalization, where in addition t...
05/28/2022

Federated Neural Bandit

Recent works on neural contextual bandit have achieved compelling perfor...