Pavel Dvurechensky

Pavel Dvurechensky

Auto-generated profile, based on publicly available information

Pavel Dvurechensky

Weierstrass Institute for Applied Analysis and Stochastics Mohrenstr. 39 10117 Berlin Germany

Research Focus & Metrics

Academic Career Length

13Years (2014-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
23 August 2016 in Journal of Optimization Theory and Applications
Verified
Journal Article
Closed access
PDF file
PDPavel Dvurechensky
Pavel Dvurechensky
AGAlexander Gasnikov
Alexander Gasnikov

9 July 2021 in Optimization Methods and Software
Verified
Journal Article
Closed access
FSFedor Stonyakin
Fedor Stonyakin
ATAlexander Tyurin
Alexander Tyurin
AGAlexander Gasnikov
Alexander Gasnikov
PDPavel Dvurechensky
Pavel Dvurechensky
AAArtem Agafonov
Artem Agafonov
VPVictorya Piskunova
Victorya Piskunova
In this paper, we propose a general algorithmic framework for the first-order methods in optimization in a broad sense, including minimization problems, saddle-point problems and variational inequalities (VIs). This framework allows obtaining many known methods as a special case, the list including accelerated gradient method, composite optimization methods, level-set methods, Bregman proximal methods. The idea of the framework is based on constructing an inexact model of the main problem component, i.e. objective function in optimization or operator in VIs. Besides reproducing known results, our framework allows constructing new methods, which we illustrate by constructing a universal conditional gradient method and a universal method for VIs with a composite structure. This method works for smooth and non-smooth problems with optimal complexity without a priori knowledge of the problem's smoothness. As a particular case of our general framework, we introduce relative smoothness for operators and propose an algorithm for VIs with such operators. We also generalize our framework for relatively strongly convex objectives and strongly monotone VIs.

2 March 2020 in Optimization Methods and Software
Verified
Journal Article
Closed access
YNYurii Nesterov
Yurii Nesterov
AGAlexander Gasnikov
Alexander Gasnikov
SGSergey Guminov
Sergey Guminov
PDPavel Dvurechensky
Pavel Dvurechensky
In this paper, a new variant of accelerated gradient descent is proposed. The proposed method does not require any information about the objective function, uses exact line search for the practical accelerations of convergence, converges according to the well-known lower bounds for both convex and non-convex objective functions, possesses primal–dual properties and can be applied in the non-euclidian set-up. As far as we know this is the first such method possessing all of the above properties at the same time. We also present a universal version of the method which is applicable to non-smooth problems. We demonstrate how in practice one can efficiently use the combination of line-search and primal-duality by considering a convex optimization problem with a simple structure (for example, linearly constrained).

1 June 2022 in SIAM Journal on Optimization
Verified
Journal Article
Closed access
EGEduard Gorbunov
Eduard Gorbunov
PDPavel Dvurechensky
Pavel Dvurechensky
AGAlexander Gasnikov
Alexander Gasnikov
We consider an unconstrained problem of minimizing a smooth convex function which is only available through noisy observations of its values, the noise consisting of two parts. Similar to stochasti...

1 August 2017 in Computational Mathematics and Mathematical Physics
Verified
Journal Article
Closed access
PDF file
AAA. S. Anikin
A. S. Anikin
AGAlexander Gasnikov
Alexander Gasnikov
PDP. E. Dvurechensky
P. E. Dvurechensky
ATA. I. Tyurin
A. I. Tyurin
ACA. V. Chernov
A. V. Chernov
A strongly convex function of simple structure (for example, separable) is minimized under affine constraints. A dual problem is constructed and solved by applying a fast gradient method. The necessary properties of this method are established relying on which, under rather general conditions, the solution of the primal problem can be recovered with the same accuracy as the dual solution from the sequence generated by this method in the dual space of the problem. Although this approach seems natural, some previously unpublished rather subtle results necessary for its rigorous and complete theoretical substantiation in the required generality are presented.

1 March 2019 in Doklady Mathematics
Verified
Journal Article
Closed access
SGS. V. Guminov
S. V. Guminov
YNYu. E. Nesterov
Yu. E. Nesterov
PDP. E. Dvurechensky
P. E. Dvurechensky
AGA. V. Gasnikov
A. V. Gasnikov