Darina Dvinskikh
- Senior Research Fellow:Faculty of Computer Science / AI and Digital Science Institute / International Laboratory of Stochastic Algorithms and High-Dimensional Inference
- Associate Professor:Faculty of Computer Science / Big Data and Information Retrieval School
- Darina Dvinskikh has been at HSE University since 2022.
Education and Degrees
- 2021
PhD
Humboldt University of Berlin - 2018
Master's
Moscow Institute of Physics and Technology - 2016
Bachelor's
Moscow Institute of Physics and Technology
Courses (2023/2024)
- Mathematical Statistics (Bachelor’s programme; Faculty of Computer Science; 2 year, 3, 4 module)Rus
- Modern Algorithmical Optimization (Master’s programme; Faculty of Computer Science; 2 year, 2 module)Eng
- Past Courses
Courses (2022/2023)
- Mathematical Statistics (Bachelor’s programme; Faculty of Computer Science; 2 year, 3, 4 module)Rus
- Modern Algorithmical Optimization (Master’s programme; Faculty of Computer Science; 2 year, 2 module)Eng
Publications15
- Chapter Kornilov N., Shamir O., Lobanov A., Dvinskikh D., Alexander Gasnikov, Shibaev I., Gorbunov E., Horváth S. Accelerated zeroth-order method for non-smooth stochastic convex optimization problem with infinite variance, in: Advances in Neural Information Processing Systems 36 (NeurIPS 2023). Curran Associates, Inc., 2023.
- Article Rogozin A., Beznosikov A., Dvinskikh D., Kovalev D., Dvurechensky P., Gasnikov A. Decentralized saddle point problems via non-Euclidean mirror prox // Optimization Methods and Software. 2023. P. 1-26. doi
- Article Alashqar B., Gasnikov A., Dvinskikh D., Lobanov A. Gradient-free Federated Learning Methods with l1 and l2-randomization for Non-smooth Convex Stochastic Optimization Problems // Computational Mathematics and Mathematical Physics. 2023. P. 1600-1653.
- Article Sadiev A., Borodich E., Beznosikov A., Dvinskikh D., Chezhegov S., Tappenden R., Takáč M., Alexander Gasnikov. Decentralized personalized federated learning: Lower bounds and optimal algorithm for all personalization modes // EURO Journal on Computational Optimization. 2022. Vol. 10. Article 100041. doi
- Chapter Dvinskikh D., Tominin V., Tominin I., Gasnikov Alexander. Noisy Zeroth-Order Optimization for Non-smooth Saddle Point Problems, in: Mathematical Optimization Theory and Operations Research, 21st International Conference, MOTOR 2022, Petrozavodsk, Russia, July 2–6, 2022, Proceedings Vol. 13367. Cham: Springer, 2022. doi Ch. 279899. P. 18-33. doi
- Article Ivanova A., Dvurechensky P., Vorontsova E., Pasechnyuk D., Gasnikov A., Dvinskikh D., Tyurin A. Oracle Complexity Separation in Convex Optimization // Journal of Optimization Theory and Applications. 2022. Vol. 193. No. 1-3. P. 462-490. doi
- Chapter Gorbunov E., Rogozin A., Beznosikov A., Dvinskikh D., Gasnikov A. Recent Theoretical Advances in Decentralized Distributed Convex Optimization, in: High-Dimensional Optimization and Probability: With a View Towards Data Science. Springer, 2022. Ch. 191. P. 253-325. doi
- Chapter Dvinskikh D., Tiapkin D. Improved Complexity Bounds in Wasserstein Barycenter Problem, in: Proceedings of Machine Learning Research Volume 130: International Conference on Artificial Intelligence and Statistics. , 2021. P. 1738-1746.
- Article Stonyakin F., Tyurin A., Gasnikov A., Dvurechensky P., Agafonov A., Dvinskikh D., Alkousa M., Pasechnyuk D., Artamonov S., Piskunova V. Inexact model: a framework for optimization and variational inequalities // Optimization Methods and Software. 2021. Vol. 36. No. 6. P. 1155-1201. doi
- Article Dvinskikh D. Stochastic approximation versus sample average approximation for Wasserstein barycenters // Optimization Methods and Software. 2021 doi
- Preprint Ivanova A., Gasnikov A., Dvurechensky P., Тюрин А. И., Воронцова Е., Пасечнюк Д., Dvinskikh D. Oracle Complexity Separation in Convex Optimization / Working papers by Cornell University.. Series - "Optimization and Control". 2020. (in press)
- Chapter Stonyakin F., Dvinskikh D., Dvurechensky P., Kroshnin A., Kuznetsova O., Agafonov A., Gasnikov A., Tyurin A., Uribe C., Pasechnyuk D., Artamonov S. Gradient Methods for Problems with Inexact Model of the Objective, in: Mathematical Optimization Theory and Operations Research, 18th International Conference, MOTOR 2019 Ekaterinburg, Russia, July 8–12, 2019 / Ed. by М. Ю. Хачай, Ю. А. Кочетов, P. M. Pardalos. Vol. 11548. Springer, 2019. P. 97-114. doi
- Chapter Dvinskikh D., Gorbunov E., Gasnikov A., Dvurechensky P., Uribe C. On Primal and Dual Approaches for Distributed Stochastic Convex Optimization over Networks, in: 2019 IEEE 58th Conference on Decision and Control (CDC). IEEE, 2019. doi P. 7435-7440. doi
- Chapter Kroshnin A., Tupitsa Nazarii, Dvinskikh D., Dvurechensky P., Gasnikov Alexander, Uribe C. A. On the Complexity of Approximating Wasserstein Barycenters, in: Proceedings of Machine Learning Research Vol. 97: International Conference on Machine Learning, 9-15 June 2019, Long Beach, California, USA. PMLR, 2019. P. 3530-3540.
- Chapter Dvurechensky P., Dvinskikh D., Gasnikov A., Uribe C., Nedic A. Decentralize and randomize: Faster algorithm for Wasserstein barycenters, in: Advances in Neural Information Processing Systems 31 (NeurIPS 2018). Neural Information Processing Systems Foundation, 2018. P. 10760-10770.
Employment history
2018–2021 Researcher/PhD, Weierstrass Institute for Applied Analysis and Stochastics. Research Group 6 "Stochastic Algorithms and Nonparametric Statistics", Berlin, Germany.
‘Every Article on NeurIPS Is Considered a Significant Result’
Staff members of the HSE Faculty of Computer Science will present 12 of their works at the 37th Conference and Workshop on Neural Information Processing Systems (NeurIPS), one of the most significant events in the field of artificial intelligence and machine learning. This year it will be held on December 10–16 in New Orleans (USA).
"I want my students to have a better understanding of the optimization algorithms after my course"
Darina Dvinskikh has been working at the Faculty of Computer Science since September. She has been hired via the tenure track programme. Darina told us how her choice of research topic for the master's thesis determined her path in science and where the Wasserstein barycenters can be useful.