DeepAI AI Chat
Log In Sign Up

Federated Averaging Langevin Dynamics: Toward a unified theory and new algorithms

by   Vincent Plassier, et al.

This paper focuses on Bayesian inference in a federated learning context (FL). While several distributed MCMC algorithms have been proposed, few consider the specific limitations of FL such as communication bottlenecks and statistical heterogeneity. Recently, Federated Averaging Langevin Dynamics (FALD) was introduced, which extends the Federated Averaging algorithm to Bayesian inference. We obtain a novel tight non-asymptotic upper bound on the Wasserstein distance to the global posterior for FALD. This bound highlights the effects of statistical heterogeneity, which causes a drift in the local updates that negatively impacts convergence. We propose a new algorithm VR-FALD* that uses control variates to correct the client drift. We establish non-asymptotic bounds showing that VR-FALD* is not affected by statistical heterogeneity. Finally, we illustrate our results on several FL benchmarks for Bayesian inference.


Behavior Mimics Distribution: Combining Individual and Group Behaviors for Federated Learning

Federated Learning (FL) has become an active and promising distributed m...

Communication-Efficient and Drift-Robust Federated Learning via Elastic Net

Federated learning (FL) is a distributed method to train a global model ...

Federated Composite Optimization

Federated Learning (FL) is a distributed learning paradigm which scales ...

A Unified Analysis of Federated Learning with Arbitrary Client Participation

Federated learning (FL) faces challenges of intermittent client availabi...

Federated Learning via Posterior Averaging: A New Perspective and Practical Algorithms

Federated learning is typically approached as an optimization problem, w...

Tackling System and Statistical Heterogeneity for Federated Learning with Adaptive Client Sampling

Federated learning (FL) algorithms usually sample a fraction of clients ...

FedPop: A Bayesian Approach for Personalised Federated Learning

Personalised federated learning (FL) aims at collaboratively learning a ...