Federated Learning with a Sampling Algorithm under Isoperimetry

by   Lukang Sun, et al.

Federated learning uses a set of techniques to efficiently distribute the training of a machine learning algorithm across several devices, who own the training data. These techniques critically rely on reducing the communication cost – the main bottleneck – between the devices and a central server. Federated learning algorithms usually take an optimization approach: they are algorithms for minimizing the training loss subject to communication (and other) constraints. In this work, we instead take a Bayesian approach for the training task, and propose a communication-efficient variant of the Langevin algorithm to sample a posteriori. The latter approach is more robust and provides more knowledge of the a posteriori distribution than its optimization counterpart. We analyze our algorithm without assuming that the target distribution is strongly log-concave. Instead, we assume the weaker log Sobolev inequality, which allows for nonconvexity.


page 1

page 2

page 3

page 4


DualFL: A Duality-based Federated Learning Algorithm with Communication Acceleration in the General Convex Regime

We propose a novel training algorithm called DualFL (Dualized Federated ...

One-Shot Federated Learning

We present one-shot federated learning, where a central server learns a ...

Towards Federated Learning: Robustness Analytics to Data Heterogeneity

Federated Learning allows remote centralized server training models with...

Federated Quantum Natural Gradient Descent for Quantum Federated Learning

The heart of Quantum Federated Learning (QFL) is associated with a distr...

Central Server Free Federated Learning over Single-sided Trust Social Networks

Federated learning has become increasingly important for modern machine ...

Optimising Communication Overhead in Federated Learning Using NSGA-II

Federated learning is a training paradigm according to which a server-ba...

Fed-Focal Loss for imbalanced data classification in Federated Learning

The Federated Learning setting has a central server coordinating the tra...

Please sign up or login with your details

Forgot password? Click here to reset