activity
20142021
most citedUniversal gradient descent

22 citations · 60 across the 14 of their papers we have counts for

collaborators

14 papers

math.OC2021★ 2 cited

Flexible Modification of Gauss-Newton Method and Its Stochastic Extension

Nikita Yudin, Alexander Gasnikov

This work presents a novel version of recently developed Gauss-Newton method for solving systems of nonlinear equations, based on upper bound of solution residual and quadratic reg…

math.OC2021★ 5 cited

Improved Exploiting Higher Order Smoothness in Derivative-free Optimization and Continuous Bandit

Vasilii Novitskii, Alexander Gasnikov

We consider -smooth (satisfies the generalized Holder condition with parameter ) stochastic convex optimization problem with zero-order one-point oracle. The best known re…

math.OC2018

Algorithmic models of human behavior and stochastic optimization

Maktagali Bektemessov, Alexander Gasnikov, Anastasia Lagunovskaya +1

In this article we describe the solutions of three problems posed at different time by Yurii Nesterov. First problem is 'Mage vs Experts': Assume that we live in some enviroment th…

math.OC2017★ 22 cited

Universal gradient descent

Alexander Gasnikov

In this book we collect many different and useful facts around gradient descent method. First of all we consider gradient descent with inexact oracle. We build a general model of o…

math.OC2017★ 8 cited

Convex optimization in Hilbert space with applications to inverse problems

Alexander Gasnikov, Sergey Kabanikhin, Ahmed Mohammed +1

In this paper we propose accelerated gradient descent schemes for convex optimization problems in Hilbert space. We consider inexact oracle case.

math.OC2017★ 7 cited

Gradient-free two-points optimal method for non smooth stochastic convex optimization problem with additional small noise

Anastasia Bayandina, Alexander Gasnikov, Fariman Guliev +1

Using double-smoothing technique and stochastic mirror descent with inexact oracle we built an optimal algorithm (up to a multiplicative factor) for two-points gradient-free non-sm…

math.OC2016★ 2 cited

Searching equillibriums in large transport networks

Alexander Gasnikov

In this Doctoral Dissertation we propose new variational principles for traffic assignment problems. So to find equillibrium we have to solve large-scale convex optimization proble…

math.OC2016

Efficient numerical methods for searching equillibriums in large transport networks

Alexander Gasnikov

We propose new variational principles for traffic assignment problems. So to find equillibrium we have to solve large-scale convex optimization problem of special type. We propose…

math.OC2016★ 1 cited

Toy model for traffic flow splitting

Mikhail Blinkin, Alexander Gasnikov, Sergey Omelchenko +1

We propose a simple dynamic model splitting users of the transport network by type of movement: personal transport and public transport. A distinctive feature proposed in the artic…

math.OC2015★ 1 cited

On the relationship between imitative logit dynamics in the population game theory and mirror descent method in the online optimization using the example of the Shortest Path Problem

Alexander Gasnikov, Anastasia Lagunovskaya, Larisa Morozova

In this paper we describe how imitative logit dynamic (rather popular in population games theory) can be interpreted in terms of mirror descent method (well known in convex optimiz…

math.OC2015★ 3 cited

Nonlinear stochastic multiarmed bandit problems with inexact oracle

Alexander Gasnikov, Ekaterina Krymova, Anastasia Lagunovskaya +2

In the paper we consider one point and two point multiarmed bamdit problems. In other words we consider the online stochastic convex optimization problems with oracle that return t…

math.OC2015

Analysis of tariff policy of a railway cargo transportation

Alexander Shananin, Michael Vaschenko, Alexander Gasnikov +2

We describe a competetive equillibrium in a railway cargo transportation model. We reduce the problem of finding this equillibrium to the solution of to mutually dual convex optimi…

math.OC2014★ 9 cited

Gradient-free prox-methods with inexact oracle for stochastic convex optimization problems on a simplex

Alexander Gasnikov, Anastasia Lagunovskaya, Ilnura Usmanova +1

In the paper we show that euclidian randomization in some situations (i.e. for gradient-free method on a simplex) can be as good as the randomization on the unit sphere in 1-norm.…

math.OC2014

About reduction of searching competetive equillibrium to the minimax problem in application to different network problems

Alexander Gasnikov

In the paper we show that an important class of multistage traffic equillibrium models (including correspondence matrix calculation, traffic assignment problem etc) and their econo…