English

Sample Optimality and All-for-all Strategies in Personalized Federated and Collaborative Learning

Optimization and Control 2022-02-02 v2

Abstract

In personalized Federated Learning, each member of a potentially large set of agents aims to train a model minimizing its loss function averaged over its local data distribution. We study this problem under the lens of stochastic optimization. Specifically, we introduce information-theoretic lower bounds on the number of samples required from all agents to approximately minimize the generalization error of a fixed agent. We then provide strategies matching these lower bounds, in the all-for-one and all-for-all settings where respectively one or all agents desire to minimize their own local function. Our strategies are based on a gradient filtering approach: provided prior knowledge on some notions of distances or discrepancies between local data distributions or functions, a given agent filters and aggregates stochastic gradients received from other agents, in order to achieve an optimal bias-variance trade-off.

Keywords

Cite

@article{arxiv.2201.13097,
  title  = {Sample Optimality and All-for-all Strategies in Personalized Federated and Collaborative Learning},
  author = {Mathieu Even and Laurent Massoulié and Kevin Scaman},
  journal= {arXiv preprint arXiv:2201.13097},
  year   = {2022}
}
R2 v1 2026-06-24T09:10:20.595Z