14 papers
Gradient-Type Methods for Optimization Problems with Polyak-Łojasiewicz Condition: Early Stopping and Adaptivity to Inexactness Parameter
Ilya A. Kuruzov, Fedor S. Stonyakin, Mohammad S. Alkousa
Due to its applications in many different places in machine learning and other connected engineering applications, the problem of minimization of a smooth function that satisfies t…
Sequential Subspace Optimization for Quasar-Convex Optimization Problems with Inexact Gradient
Ilya Kuruzov, Fedor Stonyakin
It is well-known that accelerated gradient first-order methods possess optimal complexity estimates for the class of convex smooth minimization problems. In many practical situatio…
Adaptive Mirror Descent for the Network Utility Maximization Problem
Anastasiya Ivanova, Fedor Stonyakin, Dmitry Pasechnyuk +2
Network utility maximization is the most important problem in network traffic management. Given the growth of modern communication networks, we consider the utility maximization pr…
New Version of Mirror Prox for Variational Inequalities with Adaptation to Inexactness
Fedor Stonyakin, Evgeniya Vorontsova, Mohammad Alkousa
Some adaptive analogue of the Mirror Prox method for variational inequalities is proposed. In this work we consider the adaptation not only to the value of the Lipschitz constant,…
Accelerated methods for composite non-bilinear saddle point problem
Mohammad Alkousa, Darina Dvinskikh, Fedor Stonyakin +2
Based on G. Lan's accelerated gradient sliding and general relation between the smoothness and strong convexity parameters of function under Legendre transformation we show that un…
Gradient Methods for Problems with Inexact Model of the Objective
Fedor Stonyakin, Darina Dvinskikh, Pavel Dvurechensky +8
We consider optimization methods for convex minimization problems under inexact information on the objective function. We introduce inexact model of the objective, which as a parti…