← Search

Romain Chor

2 accepted papers

2024

Lessons from Generalization Error Analysis of Federated Learning: You May Communicate Less Often!

ICML 2024poster

We investigate the generalization error of statistical learning models in a Federated Learning (FL) setting. Specifically, we study the evolution of the generalization error with the number of communication rounds $R$ between $K$ clients and a parameter server (PS), i.e. the effect on the generaliza…

2022

Rate-Distortion Theoretic Bounds on Generalization Error for Distributed Learning

NeurIPS 2022accept

In this paper, we use tools from rate-distortion theory to establish new upper bounds on the generalization error of statistical distributed learning algorithms. Specifically, there are $K$ clients whose individually chosen models are aggregated by a central server. The bounds depend on the compress…