I. V. Baran
Research Subjects
I. V. Baran has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
- Fedor Sergeevich Stonyakin
Moscow Institute of Physics and Technology
5 shared publications - Mohammad Alkousa
Innopolis University, Innopolis, Russia
2 shared publications - Seydamet S. Ablaev
VI Vernadsky Crimean Fed Univ, Simferopol 295007, Republic Of Cri, Russia
2 shared publications - Andrei Mikhailovich Raigorodskii
Moscow Institute of Physics and Technology, Dolgoprudny, Russia
1 shared publication - D. V. Makarenko
Moscow Institute of Physics and Technology (State University), Dolgoprudnyi, Russia
1 shared publication - Dmitry Arkad'EVich Pasechnyuk
Mohamed Zayed University of Artificial Intelligence Abu Dhabi UAE
1 shared publication
Latest Publications
- 1 December 2023
- Published by Pleiades Publishing Ltd in Programming and Computer Software
- Vol. 49 (6) , 493-504
Adaptive Variant of the Frank–Wolfe Algorithm for Convex Optimization Problems
In this paper, we investigate a variant of the Frank–Wolfe method for convex optimization problems with the adaptive selection of the step parameter corresponding to information about the smoothness of the objective function (the Lipschitz constant of the gradient). Theoretical estimates of the quality of the approximate solution provided by the method using adaptively selected parameters Lk are presented. For a class of problems on a convex feasible set with a convex objective function, the guaranteed convergence rate of the proposed method is sublinear. A special subclass of these problems (an objective function with the gradient dominance condition) is considered and the convergence rate of the method using adaptively selected parameters Lk is estimated. An important feature of the result obtained is the elaboration of the case where it is possible to guarantee, after the completion of the iteration, at least double reduction in the residual of the function. At the same time, the use of adaptively selected parameters in theoretical estimates makes the method applicable to both smooth and non-smooth problems, provided that the iteration termination criterion is met. For smooth problems, it can be proved that the theoretical estimates of the method are reliably optimal up to multiplication by a constant factor. Computational experiments are carried out and a comparison with two other algorithms is made to demonstrate the efficiency of the algorithm on a number of both smooth and non-smooth problems.
- 1 December 2023
- Published by Pleiades Publishing Ltd in Programming and Computer Software
- Vol. 49 (6) , 493-504
Adaptive Variant of the Frank–Wolfe Algorithm for Convex Optimization Problems
In this paper, we investigate a variant of the Frank–Wolfe method for convex optimization problems with the adaptive selection of the step parameter corresponding to information about the smoothness of the objective function (the Lipschitz constant of the gradient). Theoretical estimates of the quality of the approximate solution provided by the method using adaptively selected parameters Lk are presented. For a class of problems on a convex feasible set with a convex objective function, the guaranteed convergence rate of the proposed method is sublinear. A special subclass of these problems (an objective function with the gradient dominance condition) is considered and the convergence rate of the method using adaptively selected parameters Lk is estimated. An important feature of the result obtained is the elaboration of the case where it is possible to guarantee, after the completion of the iteration, at least double reduction in the residual of the function. At the same time, the use of adaptively selected parameters in theoretical estimates makes the method applicable to both smooth and non-smooth problems, provided that the iteration termination criterion is met. For smooth problems, it can be proved that the theoretical estimates of the method are reliably optimal up to multiplication by a constant factor. Computational experiments are carried out and a comparison with two other algorithms is made to demonstrate the efficiency of the algorithm on a number of both smooth and non-smooth problems.
- Open Access
Subgradient methods for non-smooth optimization problems with some relaxation of sharp minimum
In this paper we propose a generalized condition for a sharp minimum, somewhat similar to the inexact oracle proposed recently by Devolder-Glineur-Nesterov. The proposed approach makes it possible to extend the class of applicability of subgradient methods with the Polyak step-size, to the situation of inexact information about the value of the minimum, as well as the unknown Lipschitz constant of the objective function. Moreover, the use of local analogs of the global characteristics of the objective function makes it possible to apply the results of this type to wider classes of problems. We show the possibility of applying the proposed approach to strongly convex non-smooth problems, also, we make an experimental comparison with the known optimal subgradient method for such a class of problems. Moreover, there were obtained some results connected to the applicability of the proposed technique to some types of problems with convexity relaxations: the recently proposed notion of weak $\beta$-quasi-convexity and ordinary quasi-convexity. Also in the paper, we study a generalization of the described technique to the situation with the assumption that the $\delta$-subgradient of the objective function is available instead of the usual subgradient. For one of the considered methods, conditions are found under which, in practice, it is possible to escape the projection of the considered iterative sequence onto the feasible set of the problem.
Open AccessSubgradient methods for non-smooth optimization problems with some relaxation of sharp minimum
In this paper we propose a generalized condition for a sharp minimum, somewhat similar to the inexact oracle proposed recently by Devolder-Glineur-Nesterov. The proposed approach makes it possible to extend the class of applicability of subgradient methods with the Polyak step-size, to the situation of inexact information about the value of the minimum, as well as the unknown Lipschitz constant of the objective function. Moreover, the use of local analogs of the global characteristics of the objective function makes it possible to apply the results of this type to wider classes of problems. We show the possibility of applying the proposed approach to strongly convex non-smooth problems, also, we make an experimental comparison with the known optimal subgradient method for such a class of problems. Moreover, there were obtained some results connected to the applicability of the proposed technique to some types of problems with convexity relaxations: the recently proposed notion of weak $\beta$-quasi-convexity and ordinary quasi-convexity. Also in the paper, we study a generalization of the described technique to the situation with the assumption that the $\delta$-subgradient of the objective function is available instead of the usual subgradient. For one of the considered methods, conditions are found under which, in practice, it is possible to escape the projection of the considered iterative sequence onto the feasible set of the problem.
- 1 January 2021
- Published by Krasovskii Institute of Mathematics and Mechanics UB RAS in Trudy Instituta Matematiki i Mekhaniki UrO RAN
- Vol. 27 (4) , 175-188
Adaptive gradient-type methods for optimization problems with relative error and sharp minimum
A universal method of gradient type for convex minimization problems with relative error is studied, and new results on the linear convergence rate of specific versions of the subgradient method for problems with a sharp minimum and some generalizations of convexity are obtained. A new approach to the choice of parameters and the stopping rule of an adaptive version of the method of similar triangles on a class of minimization problems for convex positively homogeneous functionals is proposed. As a consequence, an analog of the universal gradient method for problems with relative error is obtained and an optimal estimate of its convergence rate on a chosen class of problems is proved. An example of the results of numerical experiments illustrating the possibility of improving the quality of the approximate solution produced by the method as compared to a theoretical estimate due to the introduced adaptive stopping rule is given. A version of the subgradient method for minimization problems with weakly beta-quasiconvex Lipschitz-continuous functionals in the case of a sharp minimum is considered, and a linear convergence rate is proved. Finally, a version of the subgradient method is proposed that converges at a linear rate on a class of problems of minimizing quasiconvex Holder-continuous functionals with a sharp minimum. The applicability of this result for functionals with a weak sharp minimum (Holderian growth) is shown and a corollary of this result is formulated for problems with relative error.
- 1 January 2021
- Published by Krasovskii Institute of Mathematics and Mechanics UB RAS in Trudy Instituta Matematiki i Mekhaniki UrO RAN
- Vol. 27 (4) , 175-188
Adaptive gradient-type methods for optimization problems with relative error and sharp minimum
A universal method of gradient type for convex minimization problems with relative error is studied, and new results on the linear convergence rate of specific versions of the subgradient method for problems with a sharp minimum and some generalizations of convexity are obtained. A new approach to the choice of parameters and the stopping rule of an adaptive version of the method of similar triangles on a class of minimization problems for convex positively homogeneous functionals is proposed. As a consequence, an analog of the universal gradient method for problems with relative error is obtained and an optimal estimate of its convergence rate on a chosen class of problems is proved. An example of the results of numerical experiments illustrating the possibility of improving the quality of the approximate solution produced by the method as compared to a theoretical estimate due to the introduced adaptive stopping rule is given. A version of the subgradient method for minimization problems with weakly beta-quasiconvex Lipschitz-continuous functionals in the case of a sharp minimum is considered, and a linear convergence rate is proved. Finally, a version of the subgradient method is proposed that converges at a linear rate on a class of problems of minimizing quasiconvex Holder-continuous functionals with a sharp minimum. The applicability of this result for functionals with a weak sharp minimum (Holderian growth) is shown and a corollary of this result is formulated for problems with relative error.
- Open Access
- 1 January 2021
- Published by IOP Publishing in Journal of Physics: Conference Series
- Vol. 1740 (1) , 012066
An adaptive Gradient-type Method for Composite Optimization Problems with Gradient Dominance Condition and Generalized Smoothness1
We consider an interesting class of composite optimization problems with a gradient dominance condition and introduce corresponding analogue of the recently proposed concept of an inexact oracle. This concept is applied to some classes of smooth functional.
- 1 January 2021
- Published by IOP Publishing in Journal of Physics: Conference Series
- Vol. 1740 (1) , 012066
Open AccessAn adaptive Gradient-type Method for Composite Optimization Problems with Gradient Dominance Condition and Generalized Smoothness1
We consider an interesting class of composite optimization problems with a gradient dominance condition and introduce corresponding analogue of the recently proposed concept of an inexact oracle. This concept is applied to some classes of smooth functional.
- 1 January 2020
- Published by Krasovskii Institute of Mathematics and Mechanics UB RAS in Trudy Instituta Matematiki i Mekhaniki UrO RAN
- Vol. 26 (3) , 198-+
ON SOME ALGORITHMS FOR CONSTRAINED OPTIMIZATION PROBLEMS WITH RELATIVE ACCURACY WITH RESPECT TO THE OBJECTIVE FUNCTIONAL
Convergence rate estimates are derived for some subgradient methods for the problem of minimization of a nonsmooth convex Lipschitz homogeneous functional with relative accuracy with respect to the objective functional under functional constraints. It is proposed to apply analogs of known switching subgradient schemes to such problems, which allows us to consider some classes of nonconvex problems as well. A convergence rate estimate is obtained for the adaptive mirror descent with switchings on the class of weakly alpha-quasiconvex objective functionals and constraint functionals. A convergence rate estimate of a proposed subgradient method with switchings with relative accuracy with respect to the objective functional is proved for problems of minimization of a convex homogeneous objective functional with a weakly alpha-quasiconvex constraint functional. We also consider a method for problems of minimization of a convex homogeneous Lipschitz functional with unimodal Lipschitz constraint functional and derive an estimate for its convergence rate. All convergence rate estimates proved in the paper show the optimality of the proposed algorithmic procedures from the viewpoint of the theory of lower oracle bounds.
- 1 January 2020
- Published by Krasovskii Institute of Mathematics and Mechanics UB RAS in Trudy Instituta Matematiki i Mekhaniki UrO RAN
- Vol. 26 (3) , 198-+
ON SOME ALGORITHMS FOR CONSTRAINED OPTIMIZATION PROBLEMS WITH RELATIVE ACCURACY WITH RESPECT TO THE OBJECTIVE FUNCTIONAL
Convergence rate estimates are derived for some subgradient methods for the problem of minimization of a nonsmooth convex Lipschitz homogeneous functional with relative accuracy with respect to the objective functional under functional constraints. It is proposed to apply analogs of known switching subgradient schemes to such problems, which allows us to consider some classes of nonconvex problems as well. A convergence rate estimate is obtained for the adaptive mirror descent with switchings on the class of weakly alpha-quasiconvex objective functionals and constraint functionals. A convergence rate estimate of a proposed subgradient method with switchings with relative accuracy with respect to the objective functional is proved for problems of minimization of a convex homogeneous objective functional with a weakly alpha-quasiconvex constraint functional. We also consider a method for problems of minimization of a convex homogeneous Lipschitz functional with unimodal Lipschitz constraint functional and derive an estimate for its convergence rate. All convergence rate estimates proved in the paper show the optimality of the proposed algorithmic procedures from the viewpoint of the theory of lower oracle bounds.