Eduard Gorbunov

Publication Activity (10 Years)

Years Active: 2021-2024
Publications (10 Years): 45

Top Topics

Gradient Method

Variational Inequalities

Top Venues

Publications

Saveliy Chezhegov, Yaroslav Klyukin, Andrei Semenov, Aleksandr Beznosikov, Alexander V. Gasnikov, Samuel Horváth, Martin Takác, Eduard Gorbunov
Gradient Clipping Improves AdaGrad when the Noise Is Heavy-Tailed. CoRR (2024)
Nazarii Tupitsa, Samuel Horváth, Martin Takác, Eduard Gorbunov
Federated Learning Can Find Friends That Are Beneficial. CoRR (2024)
Ahmad Rammal, Kaja Gruntkowska, Nikita Fedin, Eduard Gorbunov, Peter Richtárik
Communication Compression for Byzantine Robust Learning: New Efficient Algorithms and Improved Rates. AISTATS (2024)
Sayantan Choudhury, Nazarii Tupitsa, Nicolas Loizou, Samuel Horváth, Martin Takác, Eduard Gorbunov
Remove that Square Root: A New Efficient Scale-Invariant Version of AdaGrad. CoRR (2024)
Viktor Moskvoretskii, Nazarii Tupitsa, Chris Biemann, Samuel Horváth, Eduard Gorbunov, Irina Nikishina
Low-Resource Machine Translation through the Lens of Personalized Federated Learning. CoRR (2024)
Nikita Puchkin, Eduard Gorbunov, Nikolay Kutuzov, Alexander V. Gasnikov
Breaking the Heavy-Tailed Noise Barrier in Stochastic Optimization Problems. AISTATS (2024)
Yuriy Dorn, Nikita Kornilov, Nikolay Kutuzov, Alexander Nazin, Eduard Gorbunov, Alexander V. Gasnikov
Implicitly normalized forecaster with clipping for linear and non-linear heavy-tailed multi-armed bandits. Comput. Manag. Sci. 21 (1) (2024)
Konstantin Mishchenko, Rustem Islamov, Eduard Gorbunov, Samuel Horváth
Partially Personalized Federated Learning: Breaking the Curse of Data Heterogeneity. CoRR (2023)
Sayantan Choudhury, Eduard Gorbunov, Nicolas Loizou
Single-Call Stochastic Extragradient Methods for Structured Non-monotone Variational Inequalities: Improved Analysis under Weaker Conditions. NeurIPS (2023)
Aleksandr Beznosikov, Eduard Gorbunov, Hugo Berard, Nicolas Loizou
Stochastic Gradient Descent-Ascent: Unified Theory and New Efficient Methods. AISTATS (2023)
Sayantan Choudhury, Eduard Gorbunov, Nicolas Loizou
Single-Call Stochastic Extragradient Methods for Structured Non-monotone Variational Inequalities: Improved Analysis under Weaker Conditions. CoRR (2023)
Eduard Gorbunov, Adrien B. Taylor, Samuel Horváth, Gauthier Gidel
Convergence of Proximal Point and Extragradient-Based Methods Beyond Monotonicity: the Case of Negative Comonotonicity. ICML (2023)
Yuriy Dorn, Kornilov Nikita, Nikolay Kutuzov, Alexander Nazin, Eduard Gorbunov, Alexander V. Gasnikov
Implicitly normalized forecaster with clipping for linear and non-linear heavy-tailed multi-armed bandits. CoRR (2023)
Grigory Malinovsky, Peter Richtárik, Samuel Horváth, Eduard Gorbunov
Byzantine Robustness and Partial Participation Can Be Achieved Simultaneously: Just Clip Gradient Differences. CoRR (2023)
Abdurakhmon Sadiev, Marina Danilova, Eduard Gorbunov, Samuel Horváth, Gauthier Gidel, Pavel E. Dvurechensky, Alexander V. Gasnikov, Peter Richtárik
High-Probability Bounds for Stochastic Optimization and Variational Inequalities: the Case of Unbounded Variance. ICML (2023)
Nazarii Tupitsa, Abdulla Jasem Almansoori, Yanlin Wu, Martin Takác, Karthik Nandakumar, Samuel Horváth, Eduard Gorbunov
Byzantine-Tolerant Methods for Distributed Variational Inequalities. CoRR (2023)
Eduard Gorbunov
Unified analysis of SGD-type methods. CoRR (2023)
Nikita Kornilov, Ohad Shamir, Aleksandr V. Lobanov, Darina Dvinskikh, Alexander V. Gasnikov, Innokentiy Shibaev, Eduard Gorbunov, Samuel Horváth
Accelerated Zeroth-order Method for Non-Smooth Stochastic Convex Optimization Problem with Infinite Variance. NeurIPS (2023)
Nikita Puchkin, Eduard Gorbunov, Nikolay Kutuzov, Alexander V. Gasnikov
Breaking the Heavy-Tailed Noise Barrier in Stochastic Optimization Problems. CoRR (2023)
Eduard Gorbunov, Abdurakhmon Sadiev, Marina Danilova, Samuel Horváth, Gauthier Gidel, Pavel E. Dvurechensky, Alexander V. Gasnikov, Peter Richtárik
High-Probability Convergence for Composite and Distributed Stochastic Minimization and Variational Inequalities with Heavy-Tailed Noise. CoRR (2023)
Nazarii Tupitsa, Abdulla Jasem Almansoori, Yanlin Wu, Martin Takác, Karthik Nandakumar, Samuel Horváth, Eduard Gorbunov
Byzantine-Tolerant Methods for Distributed Variational Inequalities. NeurIPS (2023)
Nikita Fedin, Eduard Gorbunov
Byzantine-Robust Loopless Stochastic Variance-Reduced Gradient. CoRR (2023)
Abdurakhmon Sadiev, Marina Danilova, Eduard Gorbunov, Samuel Horváth, Gauthier Gidel, Pavel E. Dvurechensky, Alexander V. Gasnikov, Peter Richtárik
High-Probability Bounds for Stochastic Optimization and Variational Inequalities: the Case of Unbounded Variance. CoRR (2023)
Ahmad Rammal, Kaja Gruntkowska, Nikita Fedin, Eduard Gorbunov, Peter Richtárik
Communication Compression for Byzantine Robust Learning: New Efficient Algorithms and Improved Rates. CoRR (2023)
Sarit Khirirat, Eduard Gorbunov, Samuel Horváth, Rustem Islamov, Fakhri Karray, Peter Richtárik
Clip21: Error Feedback for Gradient Clipping. CoRR (2023)
Eduard Gorbunov, Samuel Horváth, Peter Richtárik, Gauthier Gidel
Variance Reduction is an Antidote to Byzantines: Better Rates, Weaker Assumptions and Communication Compression as a Cherry on the Top. ICLR (2023)
Eduard Gorbunov, Nicolas Loizou, Gauthier Gidel
Extragradient Method: O(1/K) Last-Iterate Convergence for Monotone Variational Inequalities and Connections With Cocoercivity. AISTATS (2022)
Aleksandr Beznosikov, Eduard Gorbunov, Hugo Berard, Nicolas Loizou
Stochastic Gradient Descent-Ascent: Unified Theory and New Efficient Methods. CoRR (2022)
Eduard Gorbunov, Hugo Berard, Gauthier Gidel, Nicolas Loizou
Stochastic Extragradient: General Analysis and Improved Rates. AISTATS (2022)
Eduard Gorbunov, Marina Danilova, David Dobre, Pavel E. Dvurechenskii, Alexander V. Gasnikov, Gauthier Gidel
Clipped Stochastic Methods for Variational Inequalities with Heavy-Tailed Noise. NeurIPS (2022)
Eduard Gorbunov, Alexander Borzunov, Michael Diskin, Max Ryabinin
Secure Distributed Training at Scale. ICML (2022)
Aleksandr Beznosikov, Boris Polyak, Eduard Gorbunov, Dmitry Kovalev, Alexander V. Gasnikov
Smooth Monotone Stochastic Variational Inequalities and Saddle Point Problems - Survey. CoRR (2022)
Eduard Gorbunov, Pavel E. Dvurechensky, Alexander V. Gasnikov
An Accelerated Method for Derivative-Free Smooth Stochastic Convex Optimization. SIAM J. Optim. 32 (2) (2022)
Eduard Gorbunov, Marina Danilova, David Dobre, Pavel E. Dvurechensky, Alexander V. Gasnikov, Gauthier Gidel
Clipped Stochastic Methods for Variational Inequalities with Heavy-Tailed Noise. CoRR (2022)
Marina Danilova, Eduard Gorbunov
Distributed Methods with Absolute Compression and Error Compensation. CoRR (2022)
Eduard Gorbunov, Samuel Horváth, Peter Richtárik, Gauthier Gidel
Variance Reduction is an Antidote to Byzantines: Better Rates, Weaker Assumptions and Communication Compression as a Cherry on the Top. CoRR (2022)
Abdurakhmon Sadiev, Grigory Malinovsky, Eduard Gorbunov, Igor Sokolov, Ahmed Khaled, Konstantin Burlachenko, Peter Richtárik
Federated Optimization Algorithms with Random Reshuffling and Gradient Compression. CoRR (2022)
Peter Richtárik, Igor Sokolov, Elnur Gasanov, Ilyas Fatkhullin, Zhize Li, Eduard Gorbunov
3PC: Three Point Compressors for Communication-Efficient Distributed Training and a Better Theory for Lazy Aggregation. ICML (2022)
Eduard Gorbunov, Adrien Taylor, Gauthier Gidel
Last-Iterate Convergence of Optimistic Gradient Method for Monotone Variational Inequalities. NeurIPS (2022)
Eduard Gorbunov
Distributed and Stochastic Optimization Methods with Gradient Compression and Local Steps. CoRR (2021)
Eduard Gorbunov, Nicolas Loizou, Gauthier Gidel
Extragradient Method: O(1/K) Last-Iterate Convergence for Monotone Variational Inequalities and Connections With Cocoercivity. CoRR (2021)
Max Ryabinin, Eduard Gorbunov, Vsevolod Plokhotnyuk, Gennady Pekhimenko
Moshpit SGD: Communication-Efficient Decentralized Training on Heterogeneous Unreliable Devices. CoRR (2021)
Eduard Gorbunov, Hugo Berard, Gauthier Gidel, Nicolas Loizou
Stochastic Extragradient: General Analysis and Improved Rates. CoRR (2021)
Max Ryabinin, Eduard Gorbunov, Vsevolod Plokhotnyuk, Gennady Pekhimenko
Moshpit SGD: Communication-Efficient Decentralized Training on Heterogeneous Unreliable Devices. NeurIPS (2021)
Eduard Gorbunov, Alexander Borzunov, Michael Diskin, Max Ryabinin
Secure Distributed Training at Scale. CoRR (2021)