Dr. Pavel Dvurechensky

I am a member of the research group Stochastic Algorithms and Nonparametric Statistics of the Weierstrass Institute for Applied Analysis and Stochastics.

Research interests

• Algorithms for large- and huge-scale optimization problems
• Optimization methods for problems with inexact oracle
• Numerical aspects of Optimal Transport distances and barycenters
• Stochastic optimization algorithms and randomized algorithms
• Algorithms for saddle-point problems and variational inequalities
• Distributed optimization
• Optimization beyond first-order methods

My research is connected to the following Mathematical Research Topics of WIAS

• Stochastic Optimization
• Optimal control of partial differential equations and nonlinear optimization
• Statistical inverse problems

Current projects

• MATH+-project EF3-3 "Optimal transport for imaging"
  Joint project with M. Hintermüller, and V. Spokoiny.

Short CV

Since 2015	Research fellow, Research Group 6 "Stochastic Algorithms and Nonparametric Statistics", WIAS, Berlin
2014 - 2015	Research assistant, Institute for Information Transmission Problems, Moscow, Russia
2009 - 2015	Junior researcher, Moscow Institute of Physics and Technology, Moscow, Russia
2013	Ph.D., Moscow Institute of Physics and Technology, Moscow, Russia
2010	Master's Diploma, Moscow Institute of Physics and Technology, Moscow, Russia
2008	Bachelor's Diploma, Moscow Institute of Physics and Technology, Moscow, Russia
Extended CV

Publications

Submitted Articles and Preprints

• F. Stonyakin, A. Gasnikov, A. Tyurin, D. Pasechnyuk, A. Agafonov, P. Dvurechensky, D. Dvinskikh, A. Kroshnin, V. Piskunova
  Inexact model: A framework for optimization and variational inequalities.
  arXiv:1902.00990
• S. Guminov, P. Dvurechensky, A. Gasnikov
  On accelerated alternating minimization.
  arXiv:1906.03622
• P. Dvurechensky, A. Gasnikov, E. Nurminsky, F. Stonyakin
  Advances in low-memory subgradient optimization.
  arXiv:1902.01572
• D. Dvinskikh, E. Gorbunov, A. Gasnikov, P. Dvurechensky, C.A. Uribe
  On primal and dual approaches for distributed stochastic convex optimization over networks.
  arXiv:1903.09844
• Y. Nesterov, A. Gasnikov, S. Guminov, P. Dvurechensky
  Primal-dual accelerated gradient methods with small-dimensional relaxation oracle.
  arXiv:1809.05895
• A. Ivanova, P. Dvurechensky, A. Gasnikov
  Composite optimization for the resource allocation problem.
  arXiv:1810.00595
• P. Dvurechensky, Y. Nesterov
  Global performance guarantees of second-order methods for unconstrained convex minimization.
  CORE Discussion Paper 2018/32, CORE UCL, 2018. pdf
• P. Dvurechensky, A. Gasnikov, F. Stonyakin, A. Titov
  Generalized Mirror Prox: Solving variational inequalities with monotone operator, inexact oracle, and unknown Hölder parameters.
  arXiv:1806.05140
• P. Dvurechensky, A. Gasnikov, E. Gorbunov
  An accelerated directional derivative method for smooth stochastic convex optimization.
  arXiv:1804.02394
• P. Dvurechensky, A. Gasnikov, E. Gorbunov
  An accelerated method for derivative-free smooth stochastic convex optimization.
  arXiv:1802.09022
• P. Dvurechensky, A. Gasnikov, D. Kamzolov
  Universal intermediate gradient method for convex problems with inexact oracle
  arXiv:1712.06036
• P. Dvurechensky, A. Gasnikov, A. Tiurin
  Randomized Similar Triangles Method: A Unifying Framework for Accelerated Randomized Optimization Methods (Coordinate Descent, Directional Search, Derivative-Free Method)
  arXiv:1707.08486
• P. Dvurechensky, A. Gasnikov, S. Omelchenko, A. Tiurin
  Adaptive Similar Triangles Method: a Stable Alternative to Sinkhorn's Algorithm for Regularized Optimal Transport
  arXiv:1706.07622
• P. Dvurechensky
  Gradient Method With Inexact Oracle for Composite Non-Convex Optimization
  arXiv:1703.09180

Selected Refereed Articles

• F.S. Stonyakin, D. Dvinskikh, P. Dvurechensky, A. Kroshnin, O. Kuznetsova, A. Agafonov, A. Gasnikov, A. Tyurin, C. Uribe, D. Pasechnyuk, S. Artamonov
  Gradient methods for problems with inexact model of the objective.
  In Mathematical Optimization Theory and Operations Research (Cham, 2019), M. Khachay, Y. Kochetov, and P. Pardalos, Eds., Springer International Publishing, pp. 97-114. arXiv:1902.09001
• A. Kroshnin, N. Tupitsa, D. Dvinskikh, P. Dvurechensky, A. Gasnikov, C. Uribe
  On the complexity of approximating Wasserstein barycenters.
  In Proceedings of the 36th International Conference on Machine Learning (Long Beach, California, USA, 09-15 Jun 2019), K. Chaudhuri and R. Salakhutdinov, Eds., vol. 97 of Proceedings of Machine Learning Research, PMLR, pp. 3530-3540. arXiv:1901.08686
• S.V. Guminov, Y.E. Nesterov, A.V. Gasnikov, P.E. Dvurechensky, F.S. Stonyakin, A.A. Titov
  Accelerated primal-dual gradient descent with linesearch for convex, nonconvex, and nonsmooth optimization problems.
  Doklady Mathematics 99, 2 (Mar 2019), 125-128.
• A.V. Gasnikov, P.E. Dvurechensky, F.S. Stonyakin, A.A. Titov
  An adaptive proximal method for variational inequalities.
  Computational Mathematics and Mathematical Physics 59, 5 (May 2019), 836-841.
• A. Gasnikov, P. Dvurechensky, E. Gorbunov, E. Vorontsova, D. Selikhanovych, C.A. Uribe, B. Jiang, H. Wang, S. Zhang, S. Bubeck, Q. Jiang, Y. T. Lee, Y. Li, A. Sidford
  Near optimal methods for minimizing convex functions with lipschitz p-th derivatives.
  In Proceedings of the Thirty-Second Conference on Learning Theory (Phoenix, USA, 25-28 Jun 2019), A. Beygelzimer and D. Hsu, Eds., vol. 99 of Proceedings of Machine Learning Research, PMLR, pp. 1392-1393. arXiv:1809.00382
• D.R. Baimurzina, A.V. Gasnikov, E.V. Gasnikova, P.E. Dvurechensky, E.I. Ershov, M.B. Kubentaeva, A.A. Lagunovskaya
  Universal method of searching for equilibria and stochastic equilibria in transportation networks.
  Computational Mathematics and Mathematical Physics 59, 1 (2019), 19-33 arXiv:1701.02473
• C. A. Uribe, D. Dvinskikh, P. Dvurechensky, A. Gasnikov, A. Nedic
  Distributed computation of Wasserstein barycenters over networks.
  In 2018 IEEE Conference on Decision and Control (CDC) (2018), pp. 6544-6549 arXiv:1803.02933
• A. V. Gasnikov, P.E. Dvurechensky, M. E. Zhukovskii, S. V. Kim, S. S. Plaunov, D. A. Smirnov, F. A. Noskov
  About the power law of the pagerank vector component distribution. Part 2. The Buckley-Osthus model, verification of the power law for this model, and setup of real search engines.
  Numerical Analysis and Applications 11, 1 (2018), 16-32.
• P. Dvurechensky, D. Dvinskikh, A. Gasnikov, C. A. Uribe, A. Nedic
  Decentralize and randomize:Faster algorithm for Wasserstein barycenters.
  In Advances in Neural Information Processing Systems 31 (2018), S. Bengio, H. Wallach, H. Larochelle, K. Grauman, N. Cesa-Bianchi, and R. Garnett, Eds., NeurIPS 2018, Curran Associates, Inc., pp. 10783-10793. arXiv:1806.03915
• P. Dvurechensky, A. Gasnikov, A. Kroshnin
  Computational optimal transport: Complexity by accelerated gradient descent is better than by Sinkhorn's algorithm
  In Proceedings of the 35th International Conference on Machine Learning (2018), J. Dy and A. Krause, Eds., vol. 80 of Proceedings of Machine Learning Research, pp. 1367-1376. arXiv:1802.04367
• P. E. Dvurechensky, A. V. Gasnikov, A. A. Lagunovskaya
  Parallel algorithms and probability of large deviation for stochastic convex optimization problems.
  Numerical Analysis and Applications 11, 1 (2018), 33-37. arXiv:1701.01830
• A. Bayandina, P. Dvurechensky, A. Gasnikov, F. Stonyakin, A. Titov
  Mirror Descent and Convex Optimization Problems With Non-Smooth Inequality Constraints
  In Large-Scale and Distributed Optimization, P. Giselsson and A. Rantzer, Eds. Springer International Publishing, 2018, ch. 8, pp. 181-215. arXiv:1710.06612
• A. V. Gasnikov, E. V. Gasnikova, P.E. Dvurechensky, A. A. M. Mohammed, E.O. Chernousova
  About the power law of the pagerank vector component distribution. Part 1. Numerical methods for finding the pagerank vector.
  Numerical Analysis and Applications 10, 4 (2017), 299-312.
• A. S. Anikin, A. V. Gasnikov, P. E. Dvurechensky, A. I. Tyurin, and A. V. Chernov
  Dual Approaches to the Minimization of Strongly Convex Functionals with a Simple Structure under Affine Constraints
  Computational Mathematics and Mathematical Physics, 2017, V. 57, No. 8, pp. 1262-1276
• L. Bogolubsky, P. Dvurechensky, A. Gasnikov, G. Gusev, Yu. Nesterov, A. Raigorodskii, A. Tikhonov, M. Zhukovskii
  Learning Supervised PageRank with Gradient-Based and Gradient-Free Optimization Methods
  In Advances in Neural Information Processing Systems 29, D. D. Lee, M. Sugiyama, U. V. Luxburg, I. Guyon, and R. Garnett, Eds. Curran Associates, Inc., 2016, pp. 4914-4922. arXiv:1603.00717
• P. Dvurechensky, A. Gasnikov
  Stochastic Intermediate Gradient Method for Convex Problems with Inexact Stochastic Oracle
  Journal of Optimization Theory and Applications, 2016 V. 171, No. 1, pp. 121-145, arXiv:1411.2876
• A. Chernov, P. Dvurechensky, A. Gasnikov
  Fast Primal-Dual Gradient Method for Strongly Convex Minimization Problems with Linear Constraints
  Kochetov, Yu. et all (eds.) Discrete Optimization and Operations Research. Proceedings of 9th International Conference,
  DOOR 2016, Vladivostok, Russia, September 19-23, 2016. LNCS: Theoretical Computer Science and General Issues,
  vol. 9869, pp. 391-403. Springer (2016), arXiv:1605.02970
• P. Dvurechensky, A. Gasnikov, E. Gasnikova, S. Matsievsky, A. Rodomanov, I. Usik
  Primal-Dual Method for Searching Equilibrium in Hierarchical Congestion Population Games
  Supplementary Proceedings of the 9th International Conference on Discrete Optimization and Operations Research
  and Scientific School (DOOR 2016) Vladivostok, Russia, September 19 - 23, 2016. pp. 584-595 http://ceur-ws.org/Vol-1623/
• Gasnikov A.V., Dvurechensky P.E., Dorn Y.V., Maximov Y.V.
  Numerical Methods for finding equilibrium flow distribution in Beckman and Stable Dynamics models
  Matematicheskoe Modelirovanie, 2016, Vol. 28, No. 10, pp. 40-64
• A. V. Gasnikov, P. E. Dvurechensky
  Stochastic Intermediate Gradient Method for Convex Optimization Problems
  Doklady Mathematics, 2016, V. 93, No. 2, pp. 1-4
• P. Dvurechensky, Yu. Nesterov, V. Spokoiny
  Primal-dual methods for solving infinite-dimensional games
  Journal of Optimization Theory and Applications, 2015 V. 166, No. 1, pp. 23-51
• P.E. Dvurechensky, G.E. Ivanov
  Algorithms for Computing Minkowski Operators and Their Application in Differential Games
  Computational Mathematics and Mathematical Physics, 2014, V. 54, No. 2, pp. 235-264

Teaching

• Recent developments in optimization methods and machine learning applications
  Humboldt University, Berlin, winter semester 2019/2020
  

Contact details

E-mail	Pavel.Dvurechensky-please remove this text-@wias-berlin.de
Phone	+49 (0) 30 20372 465
Fax	+49 (0) 30 20372 316
Address	Room 212, Weierstrass Institute, Mohrenstrasse 39, 10117 Berlin, Germany
Researchgate profile	Pavel Dvurechensky
Linkedin profile	Pavel Dvurechensky

Last updated 23.09.2019