Publications

Avetik Karagulyan, Egor Shulgin, Abdurakhmon Sadiev, Peter Richtárik (2024). SPAM: Stochastic Proximal Point Method with Momentum Variance Reduction for Non-convex Cross-Device Federated Learning. arXiv preprint arXiv:2405.20127.

PDF Cite

Peter Richtárik, Abdurakhmon Sadiev, Yury Demidovich (2024). A Unified Theory of Stochastic Proximal Point Methods without Smoothness. arXiv preprint arXiv:2405.15941.

PDF Cite

Abdurakhmon Sadiev, Laurent Condat, Peter Richtárik (2024). Stochastic proximal point methods for monotone inclusions under expected similarity. arXiv preprint arXiv:2405.14255.

PDF Cite

Eduard Gorbunov, Abdurakhmon Sadiev, Marina Danilova, Samuel Horváth, Gauthier Gidel, Pavel Dvurechensky, Alexander Gasnikov, Peter Richtárik (2023). High-Probability Convergence for Composite and Distributed Stochastic Minimization and Variational Inequalities with Heavy-Tailed Noise. arXiv preprint arXiv:2310.01860.

PDF Cite

Abdurakhmon Sadiev, Marina Danilova, Eduard Gorbunov, Samuel Horváth, Gauthier Gidel, Pavel Dvurechensky, Alexander Gasnikov, Peter Richtárik (2023). High-Probability Bounds for Stochastic Optimization and Variational Inequalities: the Case of Unbounded Variance. arXiv preprint arXiv:2302.00999.

PDF Cite

Maksim Makarenko, Elnur Gasanov, Rustem Islamov, Abdurakhmon Sadiev, Peter Richtárik (2022). Adaptive Compression for Communication-Efficient Distributed Training. arXiv preprint arXiv:2211.00188.

PDF Cite

Abdurakhmon Sadiev, Dmitry Kovalev, Peter Richárik (2022). Communication acceleration of local gradient methods via an accelerated primal-dual algorithm with inexact prox. Advances in Neural Information Processing Systems 35 (NeurIPS 2022).

PDF Cite

Abdurakhmon Sadiev, Grigory Malinovsky, Eduard Gorbunov, Igor Sokolov, Ahmed Khaled, Konstantin Burlachenko, Peter Richtárik (2022). Federated Optimization Algorithms with Random Reshuffling and Gradient Compression. arXiv preprint arXiv:2206.07021.

PDF Cite

Abdurakhmon Sadiev, Aleksandr Beznosikov, Abdulla Jasem Almansoori, Dmitry Kamzolov, Rachael Tappenden, Martin Takáč (2022). Stochastic gradient methods with preconditioned updates. arXiv preprint arXiv:2206.00285.

PDF Cite

Mohammad Alkousa, Alexander Gasnikov, Pavel Dvurechensky, Abdurakhmon Sadiev, Lama Razouk (2022). An Approach for Non-convex Uniformly Concave Structured Saddle Point Problem. Computer Research and Modeling.

PDF Cite

Dmitry Kovalev, Aleksandr Beznosikov, Abdurakhmon Sadiev, Michael Persiianov, Peter Richtárik, Alexander Gasnikov (2022). Optimal algorithms for decentralized stochastic variational inequalities. Advances in Neural Information Processing Systems 35 (NeurIPS 2022).

PDF Cite

Abdurakhmon Sadiev, Ekaterina Borodich, Aleksandr Beznosikov, Darina Dvinskikh, Saveliy Chezhegov, Rachael Tappenden, Martin Takáč, Alexander Gasnikov (2022). Decentralized personalized federated learning: Lower bounds and optimal algorithm for all personalization modes. EURO Journal on Computational Optimization.

PDF Cite

Zheng Shi, Abdurakhmon Sadiev, Nicolas Loizou, Peter Richtárik, Martin Takáč (2022). AI-SARAH: Adaptive and Implicit Stochastic Recursive Gradient Methods. arXiv preprint arXiv:2102.09700.

PDF Cite

Ekaterina Borodich, Aleksandr Beznosikov, Abdurakhmon Sadiev, Vadim Sushko, Nikolay Savelyev, Martin Takáč, Alexander Gasnikov (2021). Decentralized personalized federated min-max problems. arXiv preprint arXiv:2106.07289.

PDF Cite

Abdurakhmon Sadiev, Aleksandr Beznosikov, Pavel Dvurechensky, Alexander Gasnikov (2021). Zeroth-order algorithms for smooth saddle-point problems. Mathematical Optimization Theory and Operations Research: Recent Trends: 20th International Conference, MOTOR 2021, Irkutsk, Russia, July 5–10, 2021, Revised Selected Papers 20.

PDF Cite

Egor Gladin, Abdurakhmon Sadiev, Alexander Gasnikov, Pavel Dvurechensky, Aleksandr Beznosikov, Mohammad Alkousa (2021). Solving smooth min-min and min-max problems by mixed oracle algorithms. Mathematical Optimization Theory and Operations Research: Recent Trends: 20th International Conference, MOTOR 2021, Irkutsk, Russia, July 5–10, 2021, Revised Selected Papers 20.

PDF Cite

Aleksandr Beznosikov, Abdurakhmon Sadiev, Alexander Gasnikov (2020). Gradient-free methods with inexact oracle for convex-concave stochastic saddle-point problem. Mathematical Optimization Theory and Operations Research: 19th International Conference, MOTOR 2020, Novosibirsk, Russia, July 6–10, 2020, Revised Selected Papers 19.

PDF Cite