Alexander Tyurin
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Alexander Tyurin has a total of 16 co-authors. Here are the top co-authors by number of shared publications:
- Alexander Gasnikov
Moscow Institute of Physics and Technology
5 shared publications - Pavel Dvurechensky
Weierstrass Institute for Applied Analysis and Stochastics Mohrenstr. 39 10117 Berlin Germany
5 shared publications - Artem Agafonov
Mohamed Bin Zayed University of Artificial Intelligence (MBZUAI), Abu Dhabi, United Arab Emirates
2 shared publications - Darina Dvinskikh
HSE University Moscow Russia
2 shared publications - Dmitry Arkad'EVich Pasechnyuk
Mohamed Zayed University of Artificial Intelligence Abu Dhabi UAE
2 shared publications - Fedor Sergeevich Stonyakin
Moscow Institute of Physics and Technology
2 shared publications
Latest Publications
- 17 July 2023
- Published by Springer Nature
- p. 511-561
Unifying Framework for Accelerated Randomized Methods in Convex Optimization
- 17 July 2023
- Published by Springer Nature
- p. 511-561
Unifying Framework for Accelerated Randomized Methods in Convex Optimization
- Top Cited Papers
- 9 July 2021
- Published by Taylor & Francis in Optimization Methods and Software
- Vol. 36 (6) , 1155-1201
Inexact model: a framework for optimization and variational inequalities
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.
- 9 July 2021
- Published by Taylor & Francis in Optimization Methods and Software
- Vol. 36 (6) , 1155-1201
Top Cited PapersInexact model: a framework for optimization and variational inequalities
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.
- Open Access
Development of a method for solving structural optimization problems
In practice, optimization tasks have some structure that allows developing new algorithms for every problem with faster convergence rates. Using the structure of optimization tasks, we can propose algorithms with more optimistic convergence rates for the following optimization problems: functions with Holder continuous gradients, superposition of functions (min-max problems), transportation problems, clustering by electorial model. In this work, we propose the unification of gradient-type methods into one method using a special concept of inexact model and develop a series of methods that can solve generalized optimization problem statements and use its structure with the aid of the proposed concept of inexact model. We constructed the gradient method for problems with relative smoothness, the primal--dual adaptive gradient and fast gradient methods, and the stochastic nonadaptive gradient methods that support an inexact model of a function. Moreover, the concept of inexact model is supported by different examples of optimization problems.
Open AccessDevelopment of a method for solving structural optimization problems
In practice, optimization tasks have some structure that allows developing new algorithms for every problem with faster convergence rates. Using the structure of optimization tasks, we can propose algorithms with more optimistic convergence rates for the following optimization problems: functions with Holder continuous gradients, superposition of functions (min-max problems), transportation problems, clustering by electorial model. In this work, we propose the unification of gradient-type methods into one method using a special concept of inexact model and develop a series of methods that can solve generalized optimization problem statements and use its structure with the aid of the proposed concept of inexact model. We constructed the gradient method for problems with relative smoothness, the primal--dual adaptive gradient and fast gradient methods, and the stochastic nonadaptive gradient methods that support an inexact model of a function. Moreover, the concept of inexact model is supported by different examples of optimization problems.
- 29 June 2020
- Published by Springer Nature
- p. 406-423
A Stable Alternative to Sinkhorn’s Algorithm for Regularized Optimal Transport
- 29 June 2020
- Published by Springer Nature
- p. 406-423
A Stable Alternative to Sinkhorn’s Algorithm for Regularized Optimal Transport
- 12 June 2019
- Published by Springer Nature
- p. 97-114
Gradient Methods for Problems with Inexact Model of the Objective
- 12 June 2019
- Published by Springer Nature
- p. 97-114
Gradient Methods for Problems with Inexact Model of the Objective
- 1 August 2017
- Published by Pleiades Publishing Ltd in Computational Mathematics and Mathematical Physics
- Vol. 57 (8) , 1262-1276
Dual approaches to the minimization of strongly convex functionals with a simple structure under affine constraints
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 August 2017
- Published by Pleiades Publishing Ltd in Computational Mathematics and Mathematical Physics
- Vol. 57 (8) , 1262-1276
Dual approaches to the minimization of strongly convex functionals with a simple structure under affine constraints
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.