Publications

make your own website for free

Activations and Gradients Compression for Model-Parallel Training

Mikhail Rudakov, Aleksandr Beznosikov, Yaroslav Kholodov, Alexander Gasnikov

Doklady Rossijskoj akademii nauk. Matematika, informatika, processy upravlenia

AI Journey best paper award

December 2023

Optimal Data Splitting in Distributed Optimization for Machine Learning

Daniil Medyakov, Gleb Molodtsov, Aleksandr Beznosikov, Alexander Gasnikov

Doklady Rossijskoj akademii nauk. Matematika, informatika, processy upravlenia

December 2023

Optimal Analysis of Method with Batching for Monotone Stochastic Finite-Sum Variational Inequalities

Alexander Pichugin, Maksim Pechin, Aleksandr Beznosikov, Alexander Gasnikov

Doklady Rossijskoj akademii nauk. Matematika, informatika, processy upravlenia

December 2023

About some works of Boris Polyak on convergence of gradient methods and their development

Seydamet Ablaev, Aleksandr Beznosikov, Alexander Gasnikov, Darina Dvinskikh, Aleksandr Lobanov, Sergei Puchinin, Fedor Stonyakin

November 2023

Bregman Proximal Method for Efficient Communications under Similarity

Aleksandr Beznosikov, Darina Dvinskikh, Andrei Semenov, Alexander Gasnikov

November 2023

Ito Diffusion Approximation of Universal Ito Chains for Sampling, Optimization and Boosting

Aleksei Ustimenko, Aleksandr Beznosikov

October 2023

Real Acceleration of Communication Process in Distributed Algorithms with Compression

Svetlana Tkachenko, Artem Andreev, Aleksandr Beznosikov, Alexander Gasnikov

OPTIMA 2023 (Petrovac, Montenegro), LNCS series

September 2023

Optimal Algorithm with Complexity Separation for Strongly Convex-Strongly Concave Composite Saddle Point Problems

Ekaterina Borodich, Georgiy Kormakov, Dmitry Kovalev, Aleksandr Beznosikov, Alexander Gasnikov

July 2023

Decentralized Optimization Over Slowly Time-Varying Graphs: Algorithms and Lower Bounds

Dmitry Metelev, Aleksandr Beznosikov, Alexander Rogozin, Alexander Gasnikov, Anton Proskurnikov

Computational Management Science

July 2023

Non-smooth setting of stochastic decentralized convex optimization problem over time-varying Graphs

Aleksandr Lobanov, Andrew Veprikov, Georgiy Konin, Aleksandr Beznosikov, Alexander Gasnikov, Dmitry Kovalev

Computational Management Science

July 2023

First Order Methods with Markovian Noise: from Acceleration to Variational Inequalities

Aleksandr Beznosikov, Sergey Samsonov, Marina Sheshukova, Alexander Gasnikov, Alexey Naumov, Eric Moulines

Poster at NeurIPS 2023 (virtual)

May 2023

Sarah Frank-Wolfe: Methods for Constrained Optimization with Best Rates and Practical Features

Aleksandr Beznosikov, David Dobre, Gauthier Gidel

April 2023

Similarity, Compression and Local Steps: Three Pillars of Efficient Communications for Distributed Variational Inequalities

Aleksandr Beznosikov, Martin Takac, Alexander Gasnikov

Poster at NeurIPS 2023 (virtual)

February 2023

Randomized gradient-free methods in convex optimization

Alexander Gasnikov, Darina Dvinskikh, Pavel Dvurechensky, Eduard Gorbunov, Aleksander Beznosikov, Alexander Lobanov

November 2022

Decentralized optimization over time-varying graphs: a survey

Alexander Rogozin, Alexander Gasnikov, Aleksandr Beznosikov, Dmitry Kovalev

October 2022

SARAH-based Variance-reduced Algorithm for Stochastic Finite-sum Cocoercive Variational Inequalities

Aleksandr Beznosikov, Alexander Gasnikov

Springer Optimization and Its Applications

October 2022

Smooth Monotone Stochastic Variational Inequalities and Saddle Point Problems - Survey

Aleksandr Beznosikov, Boris Polyak, Eduard Gorbunov, Dmitry Kovalev, Alexander Gasnikov

EMS Magazine

August 2022

Compression and Data Similarity: Combination of Two Techniques for Communication-Efficient Solving of Distributed Variational Inequalities

Aleksandr Beznosikov, Alexander Gasnikov

OPTIMA 2022 (Petrovac, Montenegro), LNCS series

June 2022

On Scaled Methods for Saddle Point Problems

Aleksandr Beznosikov, Aibek Alanov, Dmitry Kovalev, Martin Takáč, Alexander Gasnikov

June 2022

Stochastic Gradient Methods with Preconditioned Updates

Abdurakhmon Sadiev, Aleksandr Beznosikov, Abdulla Jasem Almansoori, Dmitry Kamzolov, Rachael Tappenden, Martin Takáč

June 2022

Optimal Gradient Sliding and its Application to Distributed Optimization Under Similarity

Dmitry Kovalev, Aleksandr Beznosikov, Ekaterina Borodich, Alexander Gasnikov, Gesualdo Scutari

Poster at NeurIPS 2022 (virtual), proceedings

May 2022

Stochastic Gradient Descent-Ascent: Unified Theory and New Efficient Methods

Aleksandr Beznosikov, Eduard Gorbunov, Hugo Berard, Nicolas Loizou

Poster at AISTATS 2023 (Valencia), proceedings

February 2022

Optimal Algorithms for Decentralized Stochastic Variational Inequalities

Dmitry Kovalev, Aleksandr Beznosikov, Abdurakhmon Sadiev, Michael Persiianov, Peter Richtárik, Alexander Gasnikov

Poster at NeurIPS 2022 (virtual), proceedings

February 2022

The Power of First-Order Smooth Optimization for Black-Box Non-Smooth Problems

Alexander Gasnikov, Anton Novitskii, Vasilii Novitskii, Farshed Abdukhakimov, Dmitry Kamzolov, Aleksandr Beznosikov, Martin Takáč, Pavel Dvurechensky, Bin Gu

Short talk at ICML 2022, proceedings

January 2022

A Unified Analysis of Variational Inequality Methods: Variance Reduction, Sampling, Quantization and Coordinate Descent

Aleksandr Beznosikov, Alexander Gasnikov, Karina Zainulina, Alexander Maslovskiy, Dmitry Pasechnyuk

Computational Mathematics and Mathematical Physics

January 2022

Random-reshuffled SARAH does not need a full gradient computations

Aleksandr Beznosikov, Martin Takac

Optimization Letters

Poster at NeurIPS 2021 Workshop on Optimization for Machine Learning (virtual)

November 2021

Distributed Methods with Compressed Communication for Solving Variational Inequalities, with Theoretical Guarantees

Aleksandr Beznosikov, Peter Richtárik, Michael Diskin, Max Ryabinin, Alexander Gasnikov

Poster at NeurIPS 2022 (virtual), proceedings

October 2021

Distributed Saddle-Point Problems Under Similarity

Aleksandr Beznosikov, Gesualdo Scutari, Alexander Rogozin, Alexander Gasnikov

Poster at NeurIPS 2021 (virtual), proceedings

July 2021

Decentralized and Personalized Federated Learning

Abdurakhmon Sadiev, Ekaterina Borodich, Aleksandr Beznosikov, Darina Dvinskikh, Martin Takac, Alexander Gasnikov

EURO Journal on Computational Optimization

Spotlight at NeurIPS 2021 Workshop on Optimization for Machine Learning (virtual)

July 2021

Near-Optimal Decentralized Algorithms for Saddle Point Problems over Time-Varying Networks

Aleksandr Beznosikov, Alexander Rogozin, Dmitry Kovalev, Alexander Gasnikov

OPTIMA 2021 (Petrovac, Montenegro), LNCS series

July 2021

One-Point Gradient-Free Methods for Composite Optimization with Applications to Distributed Optimization

Ivan Stepanov, Artyom Voronov, Aleksandr Beznosikov, Alexander Gasnikov

July 2021

Decentralized Local Stochastic Extra-Gradient for Variational Inequalities

Aleksandr Beznosikov, Pavel Dvurechensky, Anastasia Koloskova, Valentin Samokhin, Sebastian U Stich, Alexander Gasnikov

Poster at NeurIPS 2022 (virtual), proceedings

June 2021

Decentralized Personalized Federated Learning: Lower Bounds and Optimal Algorithm for All Personalization Modes

Ekaterina Borodich, Aleksandr Beznosikov, Abdurakhmon Sadiev, Vadim Sushko, Nikolay Savelyev, Martin Takac, Alexander Gasnikov

Poster at NeurIPS 2020 Workshop on New Frontiers in Federated Learning:
Privacy, Fairness, Robustness, Personalization and Data Ownership (virtual)

June 2021

One-Point Gradient-Free Methods for Smooth and Non-Smooth Saddle-Point Problems

Aleksandr Beznosikov, Vasilii Novitskii and Alexander Gasnikov

MOTOR 2021 (Irkutsk, Russia), LNCS series

March 2021

Solving smooth min-min and min-max problems by mixed oracle algorithms

Egor Gladin, Abdurakhmon Sadiev, Alexander Gasnikov, Pavel Dvurechensky, Aleksandr Beznosikov, Mohammad Alkousa

MOTOR 2021 (Irkutsk, Russia), CCIS series

March 2021

Distributed Saddle-Point Problems: Lower Bounds, Optimal Algorithms and Robust Algorithms

Aleksandr Beznosikov, Valentin Samokhin and Alexander Gasnikov

February 2021

Decentralized Distributed Optimization for Saddle Point Problems

Alexander Rogozin, Aleksandr Beznosikov, Darina Dvinskikh, Dmitry Kovalev, Pavel Dvurechensky and Alexander Gasnikov

February 2021

Recent theoretical advances in decentralized distributed convex optimization

Eduard Gorbunov, Alexander Rogozin, Aleksandr Beznosikov, Darina Dvinskikh, Alexander Gasnikov

High Dimensional Optimization and Probability Journal

November 2020

Zeroth-Order Algorithms for Smooth Saddle-Point Problems

Abdurakhmon Sadiev, Aleksandr Beznosikov, Pavel Dvurechensky, Alexander Gasnikov

MOTOR 2021 (Irkutsk, Russia), CCIS series

September 2020

Linearly Convergent Gradient-Free Methods for Minimization of Symmetric Parabolic Approximation

Aleksandra Bazarova, Aleksandr Beznosikov and Alexander Gasnikov

Computer Research and Modeling

September 2020

Gradient-Free Methods for Saddle-Point Problem

Aleksandr Beznosikov, Abdurakhmon Sadiev and Alexander Gasnikov

MOTOR 2020 (Novosibirsk, Russia), CCIS series

May 2020

On Biased Compression for Distributed Learning

Aleksandr Beznosikov, Samuel Horváth, Peter Richtárik and Mher Safaryan

Journal of Machine Learning Research

Oral talk at NeurIPS 2020 Workshop on Scalability, Privacy and Security in Federated Learning (virtual)

Febuary 2020

Derivative-Free Method For Decentralized Distributed Non-Smooth Optimization

Aleksandr Beznosikov, Eduard Gorbunov and Alexander Gasnikov

Poster at IFAC World Congress 2020 (Berlin, Germany), IFAC Papers Online

November 2019

© 2020-2024 Aleksandr Beznosikov