activity
20142026
most citedComputational Optimal Transport: Complexity by Accelerated Gradient Descent Is Better Than by Sinkhorn's Algorithm

66 citations · 450 across the 76 of their papers we have counts for

collaborators
Showing 2017Show all

7 papers · 1 filter

math.OC2017

Universal Intermediate Gradient Method for Convex Problems with Inexact Oracle

Dmitry Kamzolov, Pavel Dvurechensky, Alexander Gasnikov

In this paper, we propose new first-order methods for minimization of a convex function on a simple convex set. We assume that the objective function is a composite function given…

math.OC2017

Mirror Descent and Convex Optimization Problems With Non-Smooth Inequality Constraints

Anastasia Bayandina, Pavel Dvurechensky, Alexander Gasnikov +2

We consider the problem of minimization of a convex function on a simple set with convex non-smooth inequality constraint and describe first-order methods to solve such problems in…

math.OC2017

Unifying Framework for Accelerated Randomized Methods in Convex Optimization

Pavel Dvurechensky, Alexander Gasnikov, Alexander Tiurin +1

In this paper, we consider smooth convex optimization problems with simple constraints and inexactness in the oracle information such as value, partial or directional derivatives o…

math.OC2017★ 11 cited

Adaptive Similar Triangles Method: a Stable Alternative to Sinkhorn's Algorithm for Regularized Optimal Transport

Pavel Dvurechensky, Alexander Gasnikov, Sergey Omelchenko +1

In this paper, we are motivated by two important applications: entropy-regularized optimal transport problem and road or IP traffic demand matrix estimation by entropy model. Both…

math.OC2017★ 1 cited

Gradient Method With Inexact Oracle for Composite Non-Convex Optimization

Pavel Dvurechensky

In this paper, we develop new first-order method for composite non-convex minimization problems with simple constraints and inexact oracle. The objective function is given as a sum…

math.OC2017

Parallel algorithms and probability of large deviation for stochastic optimization problems

Pavel Dvurechensky, Alexander Gasnikov, Anastasia Lagunovskaya

We consider convex stochastic optimization problems under different assumptions on the properties of available stochastic subgradient. It is known that, if the value of the objecti…

math.OC2017★ 5 cited

Universal similar triangulars method for searching equilibriums in traffic flow distribution models

Dilyara Baimurzina, Alexander Gasnikov, Evgenia Gasnikova +4

We describe how primal-dual version of Nesterov's Universal Method (with one projection) can be applied to solve the dual problem for the problem of searching equilibrium traffic f…