DeepAI AI Chat
Log In Sign Up

Communication Efficient Federated Learning for Generalized Linear Bandits

by   Chuanhao Li, et al.

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.


page 1

page 2

page 3

page 4


Asynchronous Upper Confidence Bound Algorithms for Federated Linear Bandits

Linear contextual bandit is a popular online learning problem. It has be...

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

Bilevel Optimization has witnessed notable progress recently with new em...

Communication Efficient Distributed Learning for Kernelized Contextual Bandits

We tackle the communication efficiency challenge of learning kernelized ...

Federated Multi-Armed Bandits

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

FedSynth: Gradient Compression via Synthetic Data in Federated Learning

Model compression is important in federated learning (FL) with large mod...

Kernel-based Federated Learning with Personalization

We consider federated learning with personalization, where in addition t...

Federated Neural Bandit

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