Home

Publications

  1. CaCuTe: Casual Cubic-Model Technique for Faster Optimization
    Nazarii Tupitsa. SIGKDD 2026 Research Track (Cycle 2), 2026.
  2. Byzantine-Tolerant Methods for Distributed Variational Inequalities
    Nazarii Tupitsa, Abdulla Jasem Almansoori, Yanlin Wu, Martin Takac, Karthik Nandakumar, Samuel Horváth, and Eduard Gorbunov. Advances in Neural Information Processing Systems, NeurIPS, 36, 2023.
  3. Methods for Convex (L0, L1)-Smooth Optimization: Clipping, Acceleration, and Adaptivity
    Eduard Gorbunov*, Nazarii Tupitsa*, Sayantan Choudhury, Alen Aliev, Peter Richtárik, Samuel Horváth, and Martin Takáč. In The Thirteenth International Conference on Learning Representations, 2025.
  4. Selective Collaboration for Robust Federated Learning
    Nazarii Tupitsa, Samuel Horváth, Martin Takáč, and Eduard Gorbunov. In The Third Conference on Parsimony and Learning (Proceedings Track), 2026.
  5. Multimarginal Optimal Transport by Accelerated Alternating Minimization
    Nazarii Tupitsa, Pavel E. Dvurechensky, Alexander V. Gasnikov, and César A. Uribe. In 59th IEEE Conference on Decision and Control (CDC 2020), pages 6132–6137, 2020.
  6. Alternating Minimization Methods for Strongly Convex Optimization
    Nazarii Tupitsa, Pavel Dvurechensky, Alexander Gasnikov, and Sergey Guminov. Journal of Inverse and Ill-posed Problems, 29(5):721–739, 2021.
  7. Computational Optimal Transport
    Nazarii Tupitsa, Pavel Dvurechensky, Darina Dvinskikh, and Alexander Gasnikov. Encyclopedia of Optimization, Springer, 2023.
  8. Remove That Square Root: A New Efficient Scale-Invariant Version of AdaGrad
    Sayantan Choudhury, Nazarii Tupitsa, Nicolas Loizou, Samuel Horváth, Martin Takac, and Eduard Gorbunov. Advances in Neural Information Processing Systems, 37, pages 47400–47431, 2024.
  9. Low-Resource Machine Translation through the Lens of Personalized Federated Learning
    Viktor Moskvoretskii, Nazarii Tupitsa, Chris Biemann, Samuel Horváth, Eduard Gorbunov, and Irina Nikishina. Findings of the Association for Computational Linguistics: EMNLP 2024, pages 8806–8825, 2024.
  10. Primal-Dual Gradient Methods for Searching Network Equilibria in Combined Models with Nested Choice Structure and Capacity Constraints
    Meruza Kubentayeva, Demyan Yarmoshik, Mikhail Persiianov, Alexey Kroshnin, Ekaterina Kotliarova, Nazarii Tupitsa, Dmitry Pasechnyuk, Alexander Gasnikov, Vladimir Shvetsov, Leonid Baryshev, et al. Computational Management Science, 21(1):15, 2024.
  11. On a Combination of Alternating Minimization and Nesterov’s Momentum
    Sergey Guminov, Pavel Dvurechensky, Nazarii Tupitsa, and Alexander Gasnikov. In Proceedings of the 38th International Conference on Machine Learning (ICML 2021), 2021.
  12. Strongly Convex Optimization for the Dual Formulation of Optimal Transport
    Nazarii Tupitsa, Alexander Gasnikov, Pavel Dvurechensky, and Sergey Guminov. In Mathematical Optimization Theory and Operations Research (MOTOR 2020), pages 192–204, 2020.
  13. On Accelerated Adaptive Methods and Their Modifications for Alternating Minimization
    Nazarii Tupitsa. Computer Research and Modeling, 14(2):497–515, 2022.
  14. Accelerated Meta-Algorithm for Convex Optimization Problems
    A. V. Gasnikov, D. M. Dvinskikh, P. E. Dvurechensky, D. I. Kamzolov, V. V. Matyukhin, D. A. Pasechnyuk, N. K. Tupitsa, and A. V. Chernov. Computational Mathematics and Mathematical Physics, 61(1):17–28, 2021.
  15. On Accelerated Methods for Tensor Canonical Polyadic Decomposition
    Daniil Merkulov and Nazarii Tupitsa. Proceedings of MIPT, 12(4(48)):61–71, 2020.

Preprints

  1. On Solving Minimization and Min-Max Problems by First-Order Methods with Relative Error in Gradients
    Artem Vasin, Valery Krivchenko, Dmitry Kovalev, Fedyor Stonyakin, Nazarii Tupitsa, Pavel Dvurechensky, Mohammad Alkousa, Nikita Kornilov, and Alexander Gasnikov. arXiv, 2025.