English

Communication Compression for Byzantine Robust Learning: New Efficient Algorithms and Improved Rates

Optimization and Control 2024-03-12 v2 Machine Learning

Abstract

Byzantine robustness is an essential feature of algorithms for certain distributed optimization problems, typically encountered in collaborative/federated learning. These problems are usually huge-scale, implying that communication compression is also imperative for their resolution. These factors have spurred recent algorithmic and theoretical developments in the literature of Byzantine-robust learning with compression. In this paper, we contribute to this research area in two main directions. First, we propose a new Byzantine-robust method with compression - Byz-DASHA-PAGE - and prove that the new method has better convergence rate (for non-convex and Polyak-Lojasiewicz smooth optimization problems), smaller neighborhood size in the heterogeneous case, and tolerates more Byzantine workers under over-parametrization than the previous method with SOTA theoretical convergence guarantees (Byz-VR-MARINA). Secondly, we develop the first Byzantine-robust method with communication compression and error feedback - Byz-EF21 - along with its bidirectional compression version - Byz-EF21-BC - and derive the convergence rates for these methods for non-convex and Polyak-Lojasiewicz smooth case. We test the proposed methods and illustrate our theoretical findings in the numerical experiments.

Keywords

Cite

@article{arxiv.2310.09804,
  title  = {Communication Compression for Byzantine Robust Learning: New Efficient Algorithms and Improved Rates},
  author = {Ahmad Rammal and Kaja Gruntkowska and Nikita Fedin and Eduard Gorbunov and Peter Richtárik},
  journal= {arXiv preprint arXiv:2310.09804},
  year   = {2024}
}

Comments

47 pages, 10 figures

R2 v1 2026-06-28T12:50:59.251Z