Abdurakhmon Sadiev

27 papers A* 5Journal 22
YearRankTypeTitle / Venue / Authors
2025 J jnl
Bernoulli-LoRA: A Theoretical Framework for Randomized Low-Rank Adaptation.
CoRR
Igor Sokolov, Abdurakhmon Sadiev, Yury Demidovich, Fawaz S. Al-Qahtani, Peter Richtárik
2025 J jnl
Better LMO-based Momentum Methods with Second-Order Information.
CoRR
Sarit Khirirat, Abdurakhmon Sadiev, Yury Demidovich, Peter Richtárik
2025 J jnl
Improved Convergence in Parameter-Agnostic Error Feedback through Momentum.
CoRR
Abdurakhmon Sadiev, Yury Demidovich, Igor Sokolov, Grigory Malinovsky, Sarit Khirirat, Peter Richtárik
2025 J jnl
Second-order Optimization under Heavy-Tailed Noise: Hessian Clipping and Sample Complexity Limits.
CoRR
Abdurakhmon Sadiev, Peter Richtárik, Ilyas Fatkhullin
2024 J jnl
A Unified Theory of Stochastic Proximal Point Methods without Smoothness.
CoRR
Peter Richtárik, Abdurakhmon Sadiev, Yury Demidovich
2024 J jnl
Differentially Private Random Block Coordinate Descent.
CoRR
Artavazd Maranjyan, Abdurakhmon Sadiev, Peter Richtárik
2024 A* conf
Don't Compress Gradients in Random Reshuffling: Compress Gradient Differences.
NeurIPS
Abdurakhmon Sadiev, Grigory Malinovsky, Eduard Gorbunov, Igor Sokolov, Ahmed Khaled, Konstantin Burlachenko, Peter Richtárik
2024 J jnl
Error Feedback under (L
CoRR
Sarit Khirirat, Abdurakhmon Sadiev, Artem Riabinin, Eduard Gorbunov, Peter Richtárik
2024 A* conf
High-Probability Convergence for Composite and Distributed Stochastic Minimization and Variational Inequalities with Heavy-Tailed Noise.
ICML
Eduard Gorbunov, Abdurakhmon Sadiev, Marina Danilova, Samuel Horváth, Gauthier Gidel, Pavel E. Dvurechensky, Alexander V. Gasnikov, Peter Richtárik
2024 J jnl
SPAM: Stochastic Proximal Point Method with Momentum Variance Reduction for Non-convex Cross-Device Federated Learning.
CoRR
Avetik G. Karagulyan, Egor Shulgin, Abdurakhmon Sadiev, Peter Richtárik
2024 J jnl
Stochastic Gradient Methods with Preconditioned Updates.
J. Optim. Theory Appl.
Abdurakhmon Sadiev, Aleksandr Beznosikov, Abdulla Jasem Almansoori, Dmitry Kamzolov, Rachael Tappenden, Martin Takác
2023 J jnl
AI-SARAH: Adaptive and Implicit Stochastic Recursive Gradient Methods.
Trans. Mach. Learn. Res.
Zheng Shi, Abdurakhmon Sadiev, Nicolas Loizou, Peter Richtárik, Martin Takác
2023 J jnl
Adaptive Compression for Communication-Efficient Distributed Training.
Trans. Mach. Learn. Res.
Maksim Makarenko, Elnur Gasanov, Abdurakhmon Sadiev, Rustem Islamov, Peter Richtárik
2023 A* conf
High-Probability Bounds for Stochastic Optimization and Variational Inequalities: the Case of Unbounded Variance.
ICML
Abdurakhmon Sadiev, Marina Danilova, Eduard Gorbunov, Samuel Horváth, Gauthier Gidel, Pavel E. Dvurechensky, Alexander V. Gasnikov, Peter Richtárik
2023 J jnl
High-Probability Bounds for Stochastic Optimization and Variational Inequalities: the Case of Unbounded Variance.
CoRR
Abdurakhmon Sadiev, Marina Danilova, Eduard Gorbunov, Samuel Horváth, Gauthier Gidel, Pavel E. Dvurechensky, Alexander V. Gasnikov, Peter Richtárik
2023 J jnl
High-Probability Convergence for Composite and Distributed Stochastic Minimization and Variational Inequalities with Heavy-Tailed Noise.
CoRR
Eduard Gorbunov, Abdurakhmon Sadiev, Marina Danilova, Samuel Horváth, Gauthier Gidel, Pavel E. Dvurechensky, Alexander V. Gasnikov, Peter Richtárik
2022 J jnl
Adaptive Compression for Communication-Efficient Distributed Training.
CoRR
Maksim Makarenko, Elnur Gasanov, Rustem Islamov, Abdurakhmon Sadiev, Peter Richtárik
2022 J jnl
Communication Acceleration of Local Gradient Methods via an Accelerated Primal-Dual Algorithm with Inexact Prox.
CoRR
Abdurakhmon Sadiev, Dmitry Kovalev, Peter Richtárik
2022 A* conf
Communication Acceleration of Local Gradient Methods via an Accelerated Primal-Dual Algorithm with an Inexact Prox.
NeurIPS
Abdurakhmon Sadiev, Dmitry Kovalev, Peter Richtárik
2022 J jnl
Decentralized personalized federated learning: Lower bounds and optimal algorithm for all personalization modes.
EURO J. Comput. Optim.
Abdurakhmon Sadiev, Ekaterina Borodich, Aleksandr Beznosikov, Darina Dvinskikh, Saveliy Chezhegov, Rachael Tappenden, Martin Takác, Alexander V. Gasnikov
2022 J jnl
Federated Optimization Algorithms with Random Reshuffling and Gradient Compression.
CoRR
Abdurakhmon Sadiev, Grigory Malinovsky, Eduard Gorbunov, Igor Sokolov, Ahmed Khaled, Konstantin Burlachenko, Peter Richtárik
2022 A* conf
Optimal Algorithms for Decentralized Stochastic Variational Inequalities.
NeurIPS
Dmitry Kovalev, Aleksandr Beznosikov, Abdurakhmon Sadiev, Michael Persiianov, Peter Richtárik, Alexander V. Gasnikov
2022 J jnl
Optimal Algorithms for Decentralized Stochastic Variational Inequalities.
CoRR
Dmitry Kovalev, Aleksandr Beznosikov, Abdurakhmon Sadiev, Michael Persiianov, Peter Richtárik, Alexander V. Gasnikov
2022 J jnl
Stochastic Gradient Methods with Preconditioned Updates.
CoRR
Abdurakhmon Sadiev, Aleksandr Beznosikov, Abdulla Jasem Almansoori, Dmitry Kamzolov, Rachael Tappenden, Martin Takác
2021 J jnl
Decentralized Personalized Federated Min-Max Problems.
CoRR
Aleksandr Beznosikov, Vadim Sushko, Abdurakhmon Sadiev, Alexander V. Gasnikov
2020 J jnl
Gradient-Free Methods for Saddle-Point Problem.
CoRR
Aleksandr Beznosikov, Abdurakhmon Sadiev, Alexander V. Gasnikov
2020 J jnl
Zeroth-Order Algorithms for Smooth Saddle-Point Problems.
CoRR
Abdurakhmon Sadiev, Aleksandr Beznosikov, Pavel E. Dvurechensky, Alexander V. Gasnikov