18 citations · 267 across the 76 of their papers we have counts for
11 papers · 2 filters
Bregman Proximal Method for Efficient Communications under Similarity
Aleksandr Beznosikov, Darina Dvinskikh, Dmitry Bylinkin +2
We propose a novel stochastic distributed method for both monotone and strongly monotone variational inequalities with Lipschitz operator and proper convex regularizers arising in…
Real Acceleration of Communication Process in Distributed Algorithms with Compression
Svetlana Tkachenko, Artem Andreev, Aleksandr Beznosikov +1
Modern applied optimization problems become more and more complex every day. Due to this fact, distributed algorithms that can speed up the process of solving an optimization probl…
Decentralized Optimization Over Slowly Time-Varying Graphs: Algorithms and Lower Bounds
Dmitry Metelev, Aleksandr Beznosikov, Alexander Rogozin +2
We consider a decentralized convex unconstrained optimization problem, where the cost function can be decomposed into a sum of strongly convex and smooth functions, associated with…
Decentralized conditional gradient method over time-varying graphs
Roman Vedernikov, Alexander Rogozin, Alexander Gasnikov
In this paper we study a generalization of distributed conditional gradient method to time-varying network architectures. We theoretically analyze convergence properties of the alg…
Decentralized optimization with affine constraints over time-varying networks
Demyan Yarmoshik, Alexander Rogozin, Alexander Gasnikov
The decentralized optimization paradigm assumes that each term of a finite-sum objective is privately stored by the corresponding agent. Agents are only allowed to communicate with…
Non-Smooth Setting of Stochastic Decentralized Convex Optimization Problem Over Time-Varying Graphs
Aleksandr Lobanov, Andrew Veprikov, Georgiy Konin +3
Distributed optimization has a rich history. It has demonstrated its effectiveness in many machine learning applications, etc. In this paper we study a subclass of distributed opti…
First Order Methods with Markovian Noise: from Acceleration to Variational Inequalities
Aleksandr Beznosikov, Sergey Samsonov, Marina Sheshukova +3
This paper delves into stochastic optimization problems that involve Markovian noise. We present a unified approach for the theoretical analysis of first-order gradient methods for…
Decentralized Proximal Optimization Method with Consensus Procedure
Alexander Rogozin, Anton Novitskii, Alexander Gasnikov
Decentralized optimization is well studied for smooth unconstrained problems. However, constrained problems or problems with composite terms are an open direction for research. We…
On Decentralized Nonsmooth Optimization
Savelii Chezhegov, Alexander Rogozin, Alexander Gasnikov
In decentralized optimization, several nodes connected by a network collaboratively minimize some objective function. For minimization of Lipschitz functions lower bounds are known…
Similarity, Compression and Local Steps: Three Pillars of Efficient Communications for Distributed Variational Inequalities
Aleksandr Beznosikov, Martin Takáč, Alexander Gasnikov
Variational inequalities are a broad and flexible class of problems that includes minimization, saddle point, and fixed point problems as special cases. Therefore, variational ineq…
Is Consensus Acceleration Possible in Decentralized Optimization over Slowly Time-Varying Networks?
Dmitriy Metelev, Alexander Rogozin, Dmitry Kovalev +1
We consider decentralized optimization problems where one aims to minimize a sum of convex smooth objective functions distributed between nodes in the network. The links in the net…