English

Greedy Low-Rank Gradient Compression for Distributed Learning with Convergence Guarantees

Machine Learning 2025-10-21 v4 Optimization and Control

Abstract

Distributed optimization is pivotal for large-scale signal processing and machine learning, yet communication overhead remains a major bottleneck. Low-rank gradient compression, in which the transmitted gradients are approximated by low-rank matrices to reduce communication, offers a promising remedy. Existing methods typically adopt either randomized or greedy compression strategies: randomized approaches project gradients onto randomly chosen subspaces, introducing high variance and degrading empirical performance; greedy methods select the most informative subspaces, achieving strong empirical results but lacking convergence guarantees. To address this gap, we propose GreedyLore--the first Greedy Low-Rank gradient compression algorithm for distributed learning with rigorous convergence guarantees. GreedyLore incorporates error feedback to correct the bias introduced by greedy compression and introduces a semi-lazy subspace update that ensures the compression operator remains contractive throughout all iterations. With these techniques, we prove that GreedyLore achieves a convergence rate of O(σ/NT+1/T)\mathcal{O}(\sigma/\sqrt{NT} + 1/T) under standard optimizers such as MSGD and Adam--marking the first linear speedup convergence rate for low-rank gradient compression. Extensive experiments are conducted to validate our theoretical findings.

Keywords

Cite

@article{arxiv.2507.08784,
  title  = {Greedy Low-Rank Gradient Compression for Distributed Learning with Convergence Guarantees},
  author = {Chuyan Chen and Yutong He and Pengrui Li and Weichen Jia and Kun Yuan},
  journal= {arXiv preprint arXiv:2507.08784},
  year   = {2025}
}

Comments

17 pages, 5 figures

R2 v1 2026-07-01T03:56:57.317Z