most citedStochastic Sign Descent Methods: New Algorithms and Better Theory

4 citations · 4 across the 1 of their papers we have counts for

collaborators
Showing math.OCShow all

2 papers · 1 filter

math.OC2026★ 4 cited

Stochastic Sign Descent Methods: New Algorithms and Better Theory

Mher Safaryan, Peter Richtárik

Various gradient compression schemes have been proposed to mitigate the communication cost in distributed training of large scale machine learning models. Sign-based methods, such…

math.OC2024

Det-CGD: Compressed Gradient Descent with Matrix Stepsizes for Non-Convex Optimization

Hanmin Li, Avetik Karagulyan, Peter Richtárik

This paper introduces a new method for minimizing matrix-smooth non-convex objectives through the use of novel Compressed Gradient Descent (CGD) algorithms enhanced with a matrix-v…