47 citations · 257 across the 74 of their papers we have counts for
10 papers · 1 filter
Random-reshuffled SARAH does not need a full gradient computations
Aleksandr Beznosikov, Martin Takáč
The StochAstic Recursive grAdient algoritHm (SARAH) algorithm is a variance reduced variant of the Stochastic Gradient Descent (SGD) algorithm that needs a gradient of the objectiv…
Distributed Methods with Compressed Communication for Solving Variational Inequalities, with Theoretical Guarantees
Aleksandr Beznosikov, Peter Richtárik, Michael Diskin +2
Variational inequalities in general and saddle point problems in particular are increasingly relevant in machine learning applications, including adversarial learning, GANs, transp…
Distributed Saddle-Point Problems Under Similarity
Aleksandr Beznosikov, Gesualdo Scutari, Alexander Rogozin +1
We study solution methods for (strongly-)convex-(strongly)-concave Saddle-Point Problems (SPPs) over networks of two type - master/workers (thus centralized) architectures and mesh…
Decentralized Personalized Federated Learning: Lower Bounds and Optimal Algorithm for All Personalization Modes
Abdurakhmon Sadiev, Ekaterina Borodich, Aleksandr Beznosikov +5
This paper considers the problem of decentralized, personalized federated learning. For centralized personalized federated learning, a penalty that measures the deviation from the…
Near-Optimal Decentralized Algorithms for Saddle Point Problems over Time-Varying Networks
Aleksandr Beznosikov, Alexander Rogozin, Dmitry Kovalev +1
Decentralized optimization methods have been in the focus of optimization community due to their scalability, increasing popularity of parallel algorithms and many applications. In…
One-Point Feedback for Composite Optimization with Applications to Distributed and Federated Learning
Aleksandr Beznosikov, Ivan Stepanov, Artyom Voronov +1
This work is devoted to solving the composite optimization problem with the mixture oracle: for the smooth part of the problem, we have access to the gradient, and for the non-smoo…
Decentralized Local Stochastic Extra-Gradient for Variational Inequalities
Aleksandr Beznosikov, Pavel Dvurechensky, Anastasia Koloskova +3
We consider distributed stochastic variational inequalities (VIs) on unbounded domains with the problem data that is heterogeneous (non-IID) and distributed across many devices. We…
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…
Solving smooth min-min and min-max problems by mixed oracle algorithms
Egor Gladin, Abdurakhmon Sadiev, Alexander Gasnikov +3
In this paper, we consider two types of problems that have some similarity in their structure, namely, min-min problems and min-max saddle-point problems. Our approach is based on…
One-Point Gradient-Free Methods for Smooth and Non-Smooth Saddle-Point Problems
Aleksandr Beznosikov, Vasilii Novitskii, Alexander Gasnikov
In this paper, we analyze gradient-free methods with one-point feedback for stochastic saddle point problems . For non-smooth and smooth cases, we present…