Papers

The papers are listed in the order they appeared online, starting with the most recent.

Dmitry Kamzolov, Dmitry Pasechnyuk, Artem Agafonov, Alexander Gasnikov, Martin Takáč (2024). OPTAMI: Global Superlinear Convergence of High-order Methods. Preprint, Under Review.
Cite Code arXiv:2410.04083
Artem Agafonov, Petr Ostroukhov, Roman Mozhaev, Konstantin Yakovlev, Eduard Gorbunov, Martin Takáč, Alexander Gasnikov, Dmitry Kamzolov (2024). Exploring Jacobian Inexactness in Second-Order Methods for Variational Inequalities: Lower Bounds, Optimal Algorithms and Quasi-Newton Approximations. In NeurIPS 2024 (Spotlight).
Cite arXiv:2405.15990
Petr Ostroukhov, Aigerim Zhumabayeva, Chulu Xiang, Alexander Gasnikov, Martin Takáč, Dmitry Kamzolov (2024). AdaBatchGrad: Combining Adaptive Batch Size and Adaptive Step Size. Preprint, Under Review.
Cite arXiv:2402.05264
Farshed Abdukhakimov, Chulu Xiang, Dmitry Kamzolov, Robert M. Gower, Martin Takáč (2023). Stochastic Gradient Descent with Preconditioned Polyak Step-size. Preprint, Under Review.
Cite arXiv:2312.17369
Farshed Abdukhakimov, Chulu Xiang, Dmitry Kamzolov, Martin Takáč (2023). Stochastic Gradient Descent with Preconditioned Polyak Step-size. Computational Mathematics and Mathematical Physics.
Cite Source Document DOI arXiv:2310.02093
Artem Agafonov, Dmitry Kamzolov, Alexander Gasnikov, Ali Kavis, Kimon Antonakopoulos, Volkan Cevher, Martin Takáč (2023). Advancing the Lower Bounds: an Accelerated, Stochastic, Second-order Method with Optimal Adaptation to Inexactness. In ICLR 2024.
Cite Poster Video Source Document arXiv:2309.01570
Dmitry Kamzolov, Klea Ziu, Artem Agafonov, Martin Takáč (2023). Accelerated Adaptive Cubic Regularized Quasi-Newton Methods. Preprint, Under Review.
Cite arXiv:2302.04987
Slavomír Hanzely, Dmitry Kamzolov, Dmitry Pasechnyuk, Alexander Gasnikov, Peter Richtárik, Martin Takáč (2022). A Damped Newton Method Achieves Global $O(\frac{1}{k^2})$ and Local Quadratic Convergence Rate. In NeurIPS 2022.
Cite Code Source Document arXiv:2211.00140
Dmitry Kamzolov, Alexander Gasnikov, Pavel Dvurechensky, Artem Agafonov, Martin Takáč (2022). Exploiting Higher-Order Derivatives in Convex Optimization Methods. In Encyclopedia of Optimization.
Cite Source Document DOI arXiv:2208.13190
Naif Alkhunaizi, Dmitry Kamzolov, Martin Takáč, Karthik Nandakumar (2022). Suppressing Poisoning Attacks on Federated Learning for Medical Imaging. In MICCAI 2022.
Cite Source Document DOI arXiv:2207.10804
Artem Agafonov, Dmitry Kamzolov, Rachael Tappenden, Alexander Gasnikov, Martin Takáč (2022). FLECS: A Federated Learning Second-Order Framework via Compression and Sketching. preprint, under review.
Cite arXiv:2206.02009
Abdurakhmon Sadiev, Aleksandr Beznosikov, Abdulla Jasem Almansoori, Dmitry Kamzolov, Rachael Tappenden, Martin Takáč (2022). Stochastic Gradient Methods with Preconditioned Updates. In JOTA.
Cite Source Document DOI arXiv:2206.00285
Alexander Gasnikov, Anton Novitskii, Vasilii Novitskii, Farshed Abdukhakimov, Dmitry Kamzolov, Aleksandr Beznosikov, Martin Takáč, Pavel Dvurechensky, Bin Gu (2022). The Power of First-Order Smooth Optimization for Black-Box Non-Smooth Problems. In ICML 2022.
Cite Source Document arXiv:2201.12289
Nikita Yudin, Dmitry Kamzolov, Vadim Sinolits, Pavel Golovkin, Alexey Erchenko (2021). Embedded Online Machine Learning. In 2021 International Conference Engineering and Telecommunication (En&T).
Cite Source Document DOI
Artem Agafonov, Pavel Dvurechensky, Gesualdo Scutari, Alexander Gasnikov, Dmitry Kamzolov, Alexander Lukashevich (2021). An Accelerated Second-Order Method for Distributed Stochastic Optimization. In 2021 60th IEEE Conference on Decision and Control (CDC).
Cite Source Document DOI arXiv:2103.14392
Pavel Dvurechensky, Dmitry Kamzolov, Alexander Lukashevich, Soomin Lee, Erik Ordentlich, César A. Uribe, Alexander Gasnikov (2021). Hyperfast Second-Order Local Solvers for Efficient Statistically Preconditioned Distributed Optimization. In EURO Journal on Computational Optimization.
Cite Source Document DOI arXiv:2102.08246
Artem Agafonov, Dmitry Kamzolov, Pavel Dvurechensky, Alexander Gasnikov, Martin Takáč (2020). Inexact Tensor Methods and Their Application to Stochastic Convex Optimization. In Optimization Methods and Software.
Cite Source Document DOI arXiv:2012.15636
Marina Danilova, Pavel Dvurechensky, Alexander Gasnikov, Eduard Gorbunov, Sergey Kamzolov, Dmitry Kamzolov, Innokentiy Shibaev (2020). Recent Theoretical Advances in Non-Convex Optimization. In High-Dimensional Optimization and Probability.
Cite Source Document DOI arXiv:2012.06188
Alexander Gasnikov, Darina Dvinskikh, Pavel Dvurechensky, Dmitry Kamzolov, Vladislav Matykhin, Dmitry Pasechnyk, Nazarii Tupitsa, Alexei Chernov (2020). Accelerated Meta-Algorithm for Convex Optimization Problems. In Computational Mathematics and Mathematical Physics.
Cite Source Document DOI arXiv:2004.08691
Dmitry Kamzolov (2020). Near-Optimal Hyperfast Second-Order Method for Convex Optimization. In Lecture Notes in Computer Science.
Cite Source Document DOI arXiv:2002.09050
Dmitry Kamzolov, Alexander Gasnikov, Pavel Dvurechensky (2020). Optimal Combination of Tensor Optimization Methods. In Lecture Notes in Computer Science.
Cite Source Document DOI arXiv:2002.01004
Anastasiya Ivanova, Pavel Dvurechensky, Alexander Gasnikov, Dmitry Kamzolov (2018). Composite Optimization for the Resource Allocation Problem. In Optimization Methods and Software.
Cite Source Document DOI arXiv:1810.00595
Dmitry Kamzolov, Pavel Dvurechensky, Alexander Gasnikov (2017). Universal Intermediate Gradient Method for Convex Problems with Inexact Oracle. In Optimization Methods and Software.
Cite Source Document DOI arXiv:1712.06036
Alexander Gasnikov, Dmitry Kamzolov, Mikhail Mendel (2016). Universal Composite Prox-Method for Strictly Convex Optimization Problems. Trudy MIPT. (in Russian).
Cite arXiv:1603.07701
Anton Anikin, Alexander Gasnikov, Alexander Gornov, Dmitry Kamzolov, Yury Maximov, Yurii Nesterov (2015). Efficient Numerical Methods to Solve Sparse Linear Equations with Application to PageRank. In Optimization Methods and Software.
Cite Source Document DOI arXiv:1508.07607
Alexander Gasnikov, Pavel Dvurechensky, Dmitry Kamzolov, Yurii Nesterov, Petr Stetsyuk, Alexandra Suvorikova, Alexey Chernov (2015). Universal Method with Inexact Oracle and its Applications for Searching Equilibriums in Multistage Transport Problems. Trudy MIPT. (in Russian).
Cite ArXiv:1506.00292
Alexander Gasnikov, Pavel Dvurechensky, Dmitry Kamzolov (2015). Gradient and Gradient-Free Methods for Stochastic Convex Optimization with Inexact Oracle. In Conference on System Dynamics and Control Processes (SDCP2014).
Cite ArXiv:1502.06259 Program