No AI summary available for this article.
Why It Matters
Sign-based methods reduce communication costs in distributed environments, but aggregating local signs can introduce bias when data are heterogeneous.
Provenance
Discovered via ArXiv and published by ArXiv.
Key Claims
Original description
Sign-based methods reduce communication costs in distributed environments, but aggregating local signs can introduce bias when data are heterogeneous. As a result, existing sign-based variance reduction methods fail to obtain the optimal convergence rates. In this paper, we solve this problem and obtain optimal rates for both nonconvex stochastic and finite-sum optimization. We first give a counterexample showing that majority voting can fail to approach stationary points even with exact local gradients. Motivated by this limitation, we propose tracking the global gradient at the server throug...
Discovered via ArXiv
Research papers and preprints from arXiv.
Publisher: arxiv.org
ID: http://arxiv.org/abs/2609.18656v1 · Indexed about 1 hour ago