activity
20242026
collaborators

5 papers

math.OC2026

Non-Euclidean SGD for Structured Optimization: Unified Analysis and Improved Rates

Dmitry Kovalev, Ekaterina Borodich

Recently, several instances of non-Euclidean SGD, including SignSGD, Lion, and Muon, have attracted significant interest from the optimization community due to their practical succ…

math.OC2025

Nesterov Finds GRAAL: Optimal and Adaptive Gradient Method for Convex Optimization

Ekaterina Borodich, Dmitry Kovalev

In this paper, we focus on the problem of minimizing a continuously differentiable convex objective function, . Recently, Malitsky (2020); Alacaoglu et al.(2023) devel…

math.OC2024

On Linear Convergence in Smooth Convex-Concave Bilinearly-Coupled Saddle-Point Optimization: Lower Bounds and Optimal Algorithms

Dmitry Kovalev, Ekaterina Borodich

We revisit the smooth convex-concave bilinearly-coupled saddle-point problem of the form . In the highly specific case whe…

math.OC2024

Lower Bounds and Optimal Algorithms for Non-Smooth Convex Decentralized Optimization over Time-Varying Networks

Dmitry Kovalev, Ekaterina Borodich, Alexander Gasnikov +1

We consider the task of minimizing the sum of convex functions stored in a decentralized manner across the nodes of a communication network. This problem is relatively well-studied…

cs.LG2024

Decentralized Personalized Federated Learning for Min-Max Problems

Ekaterina Borodich, Aleksandr Beznosikov, Abdurakhmon Sadiev +4

Personalized Federated Learning (PFL) has witnessed remarkable advancements, enabling the development of innovative machine learning applications that preserve the privacy of train…