activity
20172020
most citedMirror version of similar triangles method for constrained optimization problems

8 citations · 9 across the 3 of their papers we have counts for

collaborators

9 papers

math.OC20201 cited

Development of a method for solving structural optimization problems

Alexander Tyurin

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…

math.OC2020

Accelerated and nonaccelerated stochastic gradient descent with inexact model

Darina Dvinskikh, Alexander Tyurin, Alexander Gasnikov +1

In this paper, we propose a new way to obtain optimal convergence rates for smooth stochastic (strong) convex optimization tasks. Our approach is based on results for optimization…

math.OC2020

Accelerated and nonaccelerated stochastic gradient descent with model conception

Darina Dvinskikh, Alexander Tyurin, Alexander Gasnikov +1

In this paper, we describe a new way to get convergence rates for optimal methods in smooth (strongly) convex optimization tasks. Our approach is based on results for tasks where g…

math.OC2019

Accelerated gradient sliding and variance reduction

Darina Dvinskikh, Sergey Omelchenko, Alexander Tyurin +1

We consider sum-type strongly convex optimization problem (first term) with smooth convex not proximal friendly composite (second term). We show that the complexity of this problem…

math.OC2019

Heuristic adaptive fast gradient method in stochastic optimization tasks

Alexander Ogaltsov, Alexander Tyurin

In this paper, we present a heuristic adaptive fast gradient method. We show that in practice our method has a better convergence rate than popular today optimization methods. More…

math.OC2019

Primal-dual fast gradient method with a model

Alexander Tyurin

In this work we consider a possibility to use the conception of -model of a function for optimization tasks, whereby solving a primal problem there is a necessity to recove…