2 citations · 4 across the 6 of their papers we have counts for
Showing cs.LGShow all
2 papers · 1 filter
cs.LG2025
SGD with Adaptive Preconditioning: Unified Analysis and Momentum Acceleration
Dmitry Kovalev
In this paper, we revisit stochastic gradient descent (SGD) with AdaGrad-type preconditioning. Our contributions are twofold. First, we develop a unified convergence analysis of SG…
cs.LG2022★ 2 cited
Communication Acceleration of Local Gradient Methods via an Accelerated Primal-Dual Algorithm with Inexact Prox
Abdurakhmon Sadiev, Dmitry Kovalev, Peter Richtárik
Inspired by a recent breakthrough of Mishchenko et al (2022), who for the first time showed that local gradient steps can lead to provable communication acceleration, we propose an…