Alexander Tyurin

41 papers A* 15Journal 25Unranked 1

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Do We Need Asynchronous SGD? On the Near-Optimality of Synchronous Methods. CoRR Grigory Begunov, Alexander Tyurin
2026	J	`jnl`	Optimality in Decentralized Optimization under Bandwidth Constraints. CoRR Alexander Tyurin
2025	J	`jnl`	Asynchronous Policy Gradient Aggregation for Efficient Distributed Reinforcement Learning. CoRR Alexander Tyurin, Andrei Spiridonov, Varvara Rudenko
2025	J	`jnl`	Birch SGD: A Tree Graph Framework for Local and Asynchronous SGD Methods. CoRR Alexander Tyurin, Danil Sivtsov
2025	A*	`conf`	From Logistic Regression to the Perceptron Algorithm: Exploring Gradient Descent with Large Step Sizes. AAAI Alexander Tyurin
2025	J	`jnl`	Gradient Descent as a Perceptron Algorithm: Understanding Dynamics and Implicit Acceleration. CoRR Alexander Tyurin
2025	J	`jnl`	Learning of Population Dynamics: Inverse Optimization Meets JKO Scheme. CoRR Mikhail Persiianov, Jiawei Chen, Petr Mokrov, Alexander Tyurin, Evgeny Burnaev, Alexander Korotin
2025	J	`jnl`	Near-Optimal Convergence of Accelerated Gradient Methods under Generalized and (L CoRR Alexander Tyurin
2025	J	`jnl`	Proving the Limited Scalability of Centralized Distributed Optimization via a New Lower Bound Construction. CoRR Alexander Tyurin
2025	A*	`conf`	Ringmaster ASGD: The First Asynchronous SGD with Optimal Time Complexity. ICML Arto Maranjyan, Alexander Tyurin, Peter Richtárik
2025	J	`jnl`	Ringmaster ASGD: The First Asynchronous SGD with Optimal Time Complexity. CoRR Artavazd Maranjyan, Alexander Tyurin, Peter Richtárik
2025	A*	`conf`	Tight Time Complexities in Parallel Stochastic Optimization with Arbitrary Computation Dynamics. ICLR Alexander Tyurin
2025	A*	`conf`	Toward a Unified Theory of Gradient Descent under Generalized Smoothness. ICML Alexander Tyurin
2024	A*	`conf`	Freya PAGE: First Optimal Time Complexity for Large-Scale Nonconvex Finite-Sum Optimization with Heterogeneous Asynchronous Computations. NeurIPS Alexander Tyurin, Kaja Gruntkowska, Peter Richtárik
2024	J	`jnl`	Freya PAGE: First Optimal Time Complexity for Large-Scale Nonconvex Finite-Sum Optimization with Heterogeneous Asynchronous Computations. CoRR Alexander Tyurin, Kaja Gruntkowska, Peter Richtárik
2024	J	`jnl`	From Logistic Regression to the Perceptron Algorithm: Exploring Gradient Descent with Large Step Sizes. CoRR Alexander Tyurin
2024	A*	`conf`	Improving the Worst-Case Bidirectional Communication Complexity for Nonconvex Distributed Optimization under Function Similarity. NeurIPS Kaja Gruntkowska, Alexander Tyurin, Peter Richtárik
2024	J	`jnl`	Improving the Worst-Case Bidirectional Communication Complexity for Nonconvex Distributed Optimization under Function Similarity. CoRR Kaja Gruntkowska, Alexander Tyurin, Peter Richtárik
2024	A*	`conf`	On the Optimal Time Complexities in Decentralized Stochastic Asynchronous Optimization. NeurIPS Alexander Tyurin, Peter Richtárik
2024	A*	`conf`	Shadowheart SGD: Distributed Asynchronous SGD with Optimal Time Complexity Under Arbitrary Computation and Communication Heterogeneity. NeurIPS Alexander Tyurin, Marta Pozzi, Ivan Ilin, Peter Richtárik
2024	J	`jnl`	Shadowheart SGD: Distributed Asynchronous SGD with Optimal Time Complexity Under Arbitrary Computation and Communication Heterogeneity. CoRR Alexander Tyurin, Marta Pozzi, Ivan Ilin, Peter Richtárik
2024	J	`jnl`	Tight Time Complexities in Parallel Stochastic Optimization with Arbitrary Computation Dynamics. CoRR Alexander Tyurin
2024	J	`jnl`	Tighter Performance Theory of FedExProx. CoRR Wojciech Anyszka, Kaja Gruntkowska, Alexander Tyurin, Peter Richtárik
2023	A*	`conf`	2Direction: Theoretically Faster Distributed Training with Bidirectional Communication Compression. NeurIPS Alexander Tyurin, Peter Richtárik
2023	A*	`conf`	A Computation and Communication Efficient Method for Distributed Nonconvex Problems in the Partial Participation Setting. NeurIPS Alexander Tyurin, Peter Richtárik
2023	A*	`conf`	DASHA: Distributed Nonconvex Optimization with Communication Compression and Optimal Oracle Complexity. ICLR Alexander Tyurin, Peter Richtárik
2023	A*	`conf`	EF21-P and Friends: Improved Theoretical Communication Complexity for Distributed Optimization with Bidirectional Compression. ICML Kaja Gruntkowska, Alexander Tyurin, Peter Richtárik
2023	A*	`conf`	Momentum Provably Improves Error Feedback! NeurIPS Ilyas Fatkhullin, Alexander Tyurin, Peter Richtárik
2023	J	`jnl`	Momentum Provably Improves Error Feedback! CoRR Ilyas Fatkhullin, Alexander Tyurin, Peter Richtárik
2023	A*	`conf`	Optimal Time Complexities of Parallel Stochastic Optimization Methods Under a Fixed Computation Model. NeurIPS Alexander Tyurin, Peter Richtárik
2023	J	`jnl`	Sharper Rates and Flexible Framework for Nonconvex SGD with Client and Data Sampling. Trans. Mach. Learn. Res. Alexander Tyurin, Lukang Sun, Konstantin Burlachenko, Peter Richtárik
2022	J	`jnl`	A Computation and Communication Efficient Method for Distributed Nonconvex Problems in the Partial Participation Setting. CoRR Alexander Tyurin, Peter Richtárik
2022	J	`jnl`	DASHA: Distributed Nonconvex Optimization with Communication Compression, Optimal Oracle Complexity, and No Client Synchronization. CoRR Alexander Tyurin, Peter Richtárik
2022	J	`jnl`	EF21-P and Friends: Improved Theoretical Communication Complexity for Distributed Optimization with Bidirectional Compression. CoRR Kaja Gruntkowska, Alexander Tyurin, Peter Richtárik
2022	J	`jnl`	Modeling and cleaning RNA-seq data significantly improve detection of differentially expressed genes. BMC Bioinform. Igor V. Deyneko, Orkhan N. Mustafaev, Alexander Tyurin, Ksenya V. Zhukova, Alexander Varzari, Irina V. Goldenkova-Pavlova
2022	J	`jnl`	Oracle Complexity Separation in Convex Optimization. J. Optim. Theory Appl. Anastasiya Ivanova, Pavel E. Dvurechensky, Evgeniya A. Vorontsova, Dmitry Pasechnyuk, Alexander V. Gasnikov, Darina Dvinskikh, Alexander Tyurin
2022	A*	`conf`	Permutation Compressors for Provably Faster Distributed Nonconvex Optimization. ICLR Rafal Szlendak, Alexander Tyurin, Peter Richtárik
2022	J	`jnl`	Sharper Rates and Flexible Framework for Nonconvex SGD with Client and Data Sampling. CoRR Alexander Tyurin, Lukang Sun, Konstantin Burlachenko, Peter Richtárik
2021	J	`jnl`	Inexact model: a framework for optimization and variational inequalities. Optim. Methods Softw. Fedor S. Stonyakin, Alexander Tyurin, Alexander V. Gasnikov, Pavel E. Dvurechensky, Artem Agafonov, Darina Dvinskikh, Mohammad S. Alkousa, Dmitry Pasechnyuk, Sergei Artamonov, Victoria V. Piskunova
2021	J	`jnl`	Permutation Compressors for Provably Faster Distributed Nonconvex Optimization. CoRR Rafal Szlendak, Alexander Tyurin, Peter Richtárik
2019	—	`conf`	Gradient Methods for Problems with Inexact Model of the Objective. MOTOR Fedor S. Stonyakin, Darina Dvinskikh, Pavel E. Dvurechensky, Alexey Kroshnin, Olesya Kuznetsova, Artem Agafonov, Alexander V. Gasnikov, Alexander Tyurin, César A. Uribe, Dmitry Pasechnyuk, Sergei Artamonov