Grigory Malinovsky

37 papers A* 9A 3Journal 24Unranked 1

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Byzantine-Robust and Differentially Private Federated Optimization under Weaker Assumptions. CoRR Rustem Islamov, Grigory Malinovsky, Alexander Gaponov, Aurélien Lucchi, Peter Richtárik, Eduard Gorbunov
2025	A	`conf`	An Optimal Algorithm for Strongly Convex Min-Min Optimization. UAI Dmitry Kovalev, Alexander V. Gasnikov, Grigory Malinovsky
2025	J	`jnl`	First Provable Guarantees for Practical Private FL: Beyond Restrictive Assumptions. CoRR Egor Shulgin, Grigory Malinovsky, Sarit Khirirat, 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	A*	`conf`	MAST: model-agnostic sparsified training. ICLR Yury Demidovich, Grigory Malinovsky, Egor Shulgin, Peter Richtárik
2025	A*	`conf`	Methods with Local Steps and Random Reshuffling for Generally Smooth Non-Convex Federated Optimization. ICLR Yury Demidovich, Petr Ostroukhov, Grigory Malinovsky, Samuel Horváth, Martin Takác, Peter Richtárik, Eduard Gorbunov
2024	A*	`conf`	Byzantine Robustness and Partial Participation Can Be Achieved at Once: Just Clip Gradient Differences. NeurIPS Grigory Malinovsky, Peter Richtárik, Samuel Horváth, Eduard Gorbunov
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`	Methods with Local Steps and Random Reshuffling for Generally Smooth Non-Convex Federated Optimization. CoRR Yury Demidovich, Petr Ostroukhov, Grigory Malinovsky, Samuel Horváth, Martin Takác, Peter Richtárik, Eduard Gorbunov
2024	A*	`conf`	MicroAdam: Accurate Adaptive Optimization with Low Space Overhead and Provable Convergence. NeurIPS Ionut-Vlad Modoranu, Mher Safaryan, Grigory Malinovsky, Eldar Kurtic, Thomas Robert, Peter Richtárik, Dan Alistarh
2024	J	`jnl`	MicroAdam: Accurate Adaptive Optimization with Low Space Overhead and Provable Convergence. CoRR Ionut-Vlad Modoranu, Mher Safaryan, Grigory Malinovsky, Eldar Kurtic, Thomas Robert, Peter Richtárik, Dan Alistarh
2024	A*	`conf`	Minibatch Stochastic Three Points Method for Unconstrained Smooth Minimization. AAAI Soumia Boucherouite, Grigory Malinovsky, Peter Richtárik, El Houcine Bergou
2024	J	`jnl`	Randomized Asymmetric Chain of LoRA: The First Meaningful Theoretical Framework for Low-Rank Adaptation. CoRR Grigory Malinovsky, Umberto Michieli, Hasan Abed Al Kader Hammoud, Taha Ceritli, Hayder Elesedy, Mete Ozay, Peter Richtárik
2024	J	`jnl`	Streamlining in the Riemannian Realm: Efficient Riemannian Optimization with Loopless Variance Reduction. CoRR Yury Demidovich, Grigory Malinovsky, Peter Richtárik
2023	A*	`conf`	A Guide Through the Zoo of Biased SGD. NeurIPS Yury Demidovich, Grigory Malinovsky, Igor Sokolov, Peter Richtárik
2023	J	`jnl`	A Guide Through the Zoo of Biased SGD. CoRR Yury Demidovich, Grigory Malinovsky, Igor Sokolov, Peter Richtárik
2023	J	`jnl`	Byzantine Robustness and Partial Participation Can Be Achieved Simultaneously: Just Clip Gradient Differences. CoRR Grigory Malinovsky, Peter Richtárik, Samuel Horváth, Eduard Gorbunov
2023	A	`conf`	Can 5th Generation Local Training Methods Support Client Sampling? Yes! AISTATS Michal Grudzien, Grigory Malinovsky, Peter Richtárik
2023	J	`jnl`	Federated Learning with Regularized Client Participation. CoRR Grigory Malinovsky, Samuel Horváth, Konstantin Burlachenko, Peter Richtárik
2023	J	`jnl`	Improving Accelerated Federated Learning with Compression and Importance Sampling. CoRR Michal Grudzien, Grigory Malinovsky, Peter Richtárik
2023	J	`jnl`	MAST: Model-Agnostic Sparsified Training. CoRR Yury Demidovich, Grigory Malinovsky, Egor Shulgin, Peter Richtárik
2023	A	`conf`	Random Reshuffling with Variance Reduction: New Analysis and Better Rates. UAI Grigory Malinovsky, Alibek Sailanbayev, Peter Richtárik
2023	—	`conf`	Server-Side Stepsizes and Sampling Without Replacement Provably Help in Federated Optimization. DistributedML@CoNEXT Grigory Malinovsky, Konstantin Mishchenko, Peter Richtárik
2023	J	`jnl`	TAMUNA: Accelerated Federated Learning with Local Training and Partial Participation. CoRR Laurent Condat, Grigory Malinovsky, Peter Richtárik
2022	J	`jnl`	An Optimal Algorithm for Strongly Convex Min-min Optimization. CoRR Dmitry Kovalev, Alexander V. Gasnikov, Grigory Malinovsky
2022	J	`jnl`	Can 5 CoRR Michal Grudzien, Grigory Malinovsky, Peter Richtárik
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	J	`jnl`	Federated Random Reshuffling with Compression and Variance Reduction. CoRR Grigory Malinovsky, Peter Richtárik
2022	J	`jnl`	Minibatch Stochastic Three Points Method for Unconstrained Smooth Minimization. CoRR Soumia Boucherouite, Grigory Malinovsky, Peter Richtárik, El Houcine Bergou
2022	A*	`conf`	ProxSkip: Yes! Local Gradient Steps Provably Lead to Communication Acceleration! Finally! ICML Konstantin Mishchenko, Grigory Malinovsky, Sebastian U. Stich, Peter Richtárik
2022	J	`jnl`	ProxSkip: Yes! Local Gradient Steps Provably Lead to Communication Acceleration! Finally! CoRR Konstantin Mishchenko, Grigory Malinovsky, Sebastian U. Stich, Peter Richtárik
2022	J	`jnl`	Server-Side Stepsizes and Sampling Without Replacement Provably Help in Federated Optimization. CoRR Grigory Malinovsky, Konstantin Mishchenko, Peter Richtárik
2022	A*	`conf`	Variance Reduced ProxSkip: Algorithm, Theory and Application to Federated Learning. NeurIPS Grigory Malinovsky, Kai Yi, Peter Richtárik
2022	J	`jnl`	Variance Reduced ProxSkip: Algorithm, Theory and Application to Federated Learning. CoRR Grigory Malinovsky, Kai Yi, Peter Richtárik
2021	J	`jnl`	Random Reshuffling with Variance Reduction: New Analysis and Better Rates. CoRR Grigory Malinovsky, Alibek Sailanbayev, Peter Richtárik
2020	J	`jnl`	Distributed Proximal Splitting Algorithms with Rates and Acceleration. CoRR Laurent Condat, Grigory Malinovsky, Peter Richtárik
2020	J	`jnl`	From Local SGD to Local Fixed Point Methods for Federated Learning. CoRR Grigory Malinovsky, Dmitry Kovalev, Elnur Gasanov, Laurent Condat, Peter Richtárik