arogozin

Aleksandr Rogozin

Research Scientist
Laboratory “Multiscale Neurodynamics for Intelligent Systems”
Center for Artificial Intelligence Technology

In 2018 received B.Sc degree in Moscow Institute of Physics and Technology (MIPT). In 2020, received M.Sc degree and in 2023 a PhD in the same university. Since 2020 Alexander is working in MIPT as a Research Scientist. Research interests include convex optimization, distributed optimization.

Research interests: convex optimization, distributed optimization, time-varying communication networks.

Joint projects with industry: digital power pre-distortion (2020-2022, Huawei), internet networks planning and management (2022-2023, Huawei).

  1. Yarmoshik, D., Rogozin, A., & Gasnikov, A. (2024). Decentralized optimization with affine constraints over time-varying networks. Computational Management Science, 21(1), 10.
  2. Metelev, D., Beznosikov, A., Rogozin, A., Gasnikov, A., & Proskurnikov, A. (2024). Decentralized optimization over slowly time-varying graphs: Algorithms and lower bounds. Computational Management Science, 21(1), 8.
  3. Metelev, D., Chezhegov, S., Rogozin, A., Kovalev, D., Beznosikov, A., Sholokhov, A., & Gasnikov, A. (2024). Decentralized Finite-Sum Optimization over Time-Varying Networks. arXiv preprint arXiv:2402.02490.
  4. Rogozin, A., Beznosikov, A., Dvinskikh, D., Kovalev, D., Dvurechensky, P., & Gasnikov, A. (2024). Decentralized saddle point problems via non-Euclidean mirror prox. Optimization Methods and Software, 1-26.
  5. Metelev, D., Rogozin, A., Gasnikov, A., & Kovalev, D. (2024). Decentralized saddle-point problems with different constants of strong convexity and strong concavity. Computational Management Science, 21(1), 5.
  6. Vedernikov, R. A., Rogozin, A. V., & Gasnikov, A. V. (2023). Decentralized Conditional Gradient Method on Time-Varying Graphs. Programming and Computer Software, 49(6), 505-512.
  7. Chen, J., Lobanov, A. V., & Rogozin, A. V. (2023). Distributed min-max optimization using the smoothing technique. Компьютерные исследования и моделирование, 15(2), 469-480.
  8. Chezhegov, S., Rogozin, A., & Gasnikov, A. (2023, June). On decentralized nonsmooth optimization. In International Conference on Mathematical Optimization Theory and Operations Research (pp. 25-38). Cham: Springer Nature Switzerland.
  9. Rogozin, A., Gasnikov, A., Beznosikov, A., & Kovalev, D. (2023). Decentralized Convex Optimization over Time-Varying Graphs. In Encyclopedia of Optimization (pp. 1-17). Cham: Springer International Publishing.
  10. Nguyen, N. T., Rogozin, A., Metelev, D., & Gasnikov, A. (2023, December). Min-max optimization over slowly time-varying graphs. In Doklady Mathematics (Vol. 108, No. Suppl 2, pp. S300-S309). Moscow: Pleiades Publishing.
  11. Metelev, D., Rogozin, A., Kovalev, D., & Gasnikov, A. (2023, July). Is consensus acceleration possible in decentralized optimization over slowly time-varying networks?. In International Conference on Machine Learning (pp. 24532-24554). PMLR.
  12. Gorbunov, E., Rogozin, A., Beznosikov, A., Dvinskikh, D., & Gasnikov, A. (2022). Recent theoretical advances in decentralized distributed convex optimization. In High-Dimensional Optimization and Probability: With a View Towards Data Science (pp. 253-325). Cham: Springer International Publishing.
  13. Yarmoshik, D., Rogozin, A., Khamisov, O. O., Dvurechensky, P., & Gasnikov, A. (2022, June). Decentralized convex optimization under affine constraints for power systems control. In International Conference on Mathematical Optimization Theory and Operations Research (pp. 62-75). Cham: Springer International Publishing.
  14. Rogozin, A., Yarmoshik, D., Kopylova, K., & Gasnikov, A. (2022, September). Decentralized strongly-convex optimization with affine constraints: Primal and dual approaches. In International Conference on Optimization and Applications (pp. 93-105). Cham: Springer Nature Switzerland.
  15. Chezhegov, S., Novitskii, A., Rogozin, A., Parsegov, S., Dvurechensky, P., & Gasnikov, A. (2022). A general framework for distributed partitioned optimization. IFAC-PapersOnLine, 55(13), 139-144.
  16. Parsegov, S., Shcherbakov, P., Chebotarev, P., Erofeeva, V., & Rogozin, A. (2022). Laplacian spectra of two-layer hierarchical cyclic pursuit schemes. IFAC-PapersOnLine, 55(13), 246-251.
  17. Rogozin, A., Bochko, M., Dvurechensky, P., Gasnikov, A., & Lukoshkin, V. (2021, December). An accelerated method for decentralized distributed stochastic optimization over time-varying graphs. In 2021 60th IEEE Conference on Decision and Control (CDC) (pp. 3367-3373). IEEE.
  18. Beznosikov, A., Scutari, G., Rogozin, A., & Gasnikov, A. (2021). Distributed saddle-point problems under data similarity. Advances in Neural Information Processing Systems, 34, 8172-8184.
  19. Kovalev, D., Shulgin, E., Richtárik, P., Rogozin, A. V., & Gasnikov, A. (2021, July). ADOM: accelerated decentralized optimization method for time-varying networks. In International Conference on Machine Learning (pp. 5784-5793). PMLR.
  20. Rogozin, A., Lukoshkin, V., Gasnikov, A., Kovalev, D., & Shulgin, E. (2021). Towards accelerated rates for distributed optimization over time-varying networks. In Optimization and Applications: 12th International Conference, OPTIMA 2021, Petrovac, Montenegro, September 27–October 1, 2021, Proceedings 12 (pp. 258-272). Springer International Publishing.
  21. Beznosikov, A., Rogozin, A., Kovalev, D., & Gasnikov, A. (2021). Near-optimal decentralized algorithms for saddle point problems over time-varying networks. In Optimization and Applications: 12th International Conference, OPTIMA 2021, Petrovac, Montenegro, September 27–October 1, 2021, Proceedings 12 (pp. 246-257). Springer International Publishing.
  22. Pasechnyuk, D., Maslovskiy, A., Gasnikov, A., Anikin, A., Rogozin, A., Gornov, A., … & Begicheva, M. (2021). Non-convex optimization in digital pre-distortion of the signal. arXiv preprint arXiv:2103.10552.
  23. Trimbach, E., & Rogozin, A. (2021, July). An acceleration of decentralized sgd under general assumptions with low stochastic noise. In International Conference on Mathematical Optimization Theory and Operations Research (pp. 117-128). Cham: Springer International Publishing.
  24. Rogozin, A., & Gasnikov, A. (2020). Penalty-based method for decentralized optimization over time-varying graphs. In Optimization and Applications: 11th International Conference, OPTIMA 2020, Moscow, Russia, September 28–October 2, 2020, Proceedings 11 (pp. 239-256). Springer International Publishing.
  25. Dvinskikh, D., Gasnikov, A., Rogozin, A., & Beznosikov, A. (2020). Parallel and Distributed algorithms for ML problems. arXiv preprint arXiv:2010.09585.
  26. Rogozin, A., Uribe, C. A., Gasnikov, A. V., Malkovsky, N., & Nedić, A. (2019). Optimal distributed convex optimization on slowly time-varying graphs. IEEE Transactions on Control of Network Systems, 7(2), 829-841.

 

PhD, Moscow Institute of Physics and Technology, 2023.