6 citations · 14 across the 4 of their papers we have counts for
4 papers
Activations and Gradients Compression for Model-Parallel Training
Mikhail Rudakov, Aleksandr Beznosikov, Yaroslav Kholodov +1
Large neural networks require enormous computational clusters of machines. Model-parallel training, when the model architecture is partitioned sequentially between workers, is a po…
About some works of Boris Polyak on convergence of gradient methods and their development
Seydamet Ablaev, Aleksandr Beznosikov, Alexander Gasnikov +4
The paper presents a review of the state-of-the-art of subgradient and accelerated methods of convex optimization, including in the presence of disturbances and access to various i…
Optimal Algorithm with Complexity Separation for Strongly Convex-Strongly Concave Composite Saddle Point Problems
Ekaterina Borodich, Georgiy Kormakov, Dmitry Kovalev +2
In this work, we focuses on the following saddle point problem where is -smooth, -strongly convex, -strongly concave an…
A Unified Analysis of Variational Inequality Methods: Variance Reduction, Sampling, Quantization and Coordinate Descent
Aleksandr Beznosikov, Alexander Gasnikov, Karina Zainulina +2
In this paper, we present a unified analysis of methods for such a wide class of problems as variational inequalities, which includes minimization problems and saddle point problem…