math.OCNov 5, 2026

Compressed Per-Player Local Methods for Multiplayer Federated Learning: Exact Convergence via Increment Sharing

Authors: Bhavika Balani, TaeHo Yoon, Nicolas Loizou

Organizations: Department of Applied Mathematics & Statistics, Mathematical Institute for Data Science (MINDS), Johns Hopkins University

Abstract

Multiplayer Federated Learning (MpFL), introduced by Yoon et al. (2025), extends classical federated learning to settings where clients are rational players in a game with individual objectives and strategies, seeking an equilibrium. A natural baseline is Per-Player Local SGD (PEARL-SGD), where each player performs several local SGD steps before exchanging strategies through a central server. However, the original PEARL-SGD formulation does not extend cleanly to compressed communication. Directly compressing the players' strategies can prevent convergence to the equilibrium, even with deterministic gradients. To address this issue, we reformulate PEARL-SGD so that players communicate local strategy increments rather than the strategies themselves. Without compression, the two formulations are equivalent, but with compression, increment sharing preserves exact convergence, allowing us to design the communication-efficient compressed PEARL-SGD (C-PEARL-SGD). Beyond compression, we also consider variance reduction as another axis of improvement, introducing PEARL-SVRG and its compressed variant C-PEARL-SVRG. Under the original MpFL assumptions, we establish convergence guarantees for all variants through a unified parametric inequality. Numerical experiments, including distributed spectrum sensing, demonstrate the practical benefits of our methods over vanilla PEARL-SGD.

Figures & tables

Explore similar work

CardsList
  1. Bridging Compressed Communication and Local Steps via Spectral Method in Federated Learning

    Oct 16, 2026Dmitriy Bystrov, George Chirkov, Daniil Medyakov +2Federated LearningCommunication-Efficient Distributed Training

  2. Communication-Efficient Agnostic Federated Learning via Faster Convergence and Compression

    Sep 29, 2026Haomin Bai, Junyan Sun, Sifan Yang +2Error FeedbackOnline Federated Learning

  3. A Full Compression Pipeline for Green Federated Learning in Communication-Constrained Environments

    Apr 13, 2026Elouan Colybes, Shirin Salehi, Anke SchmeinkFederated LearningCommunication-Efficient Distributed Training