Anastasia Lagunovskaya
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Anastasia Lagunovskaya has a total of 13 co-authors. Here are the top co-authors by number of shared publications:
- Alexander Gasnikov
Moscow Institute of Physics and Technology
5 shared publications - Pavel Dvurechensky
Weierstrass Institute for Applied Analysis and Stochastics Mohrenstr. 39 10117 Berlin Germany
2 shared publications - Anastasia Bayandina
Department of Control and Applied Mathematics, Moscow Institute of Physics and Technology
1 shared publication - D. R. Baimurzina
Moscow Institute of Physics and Technology
1 shared publication - Egor Ershov
Institute for Information Transmission Problems of the Russian Academy of Sciences Moscow Russia
1 shared publication Ekaterina Krymova
1 shared publication
Latest Publications
- 1 January 2019
- Published by Pleiades Publishing Ltd in Computational Mathematics and Mathematical Physics
- Vol. 59 (1) , 19-33
Universal Method of Searching for Equilibria and Stochastic Equilibria in Transportation Networks
A universal method of searching for usual and stochastic equilibria in congestion population games is proposed. The Beckmann and stable dynamics models of an equilibrium flow distribution...
- 1 January 2019
- Published by Pleiades Publishing Ltd in Computational Mathematics and Mathematical Physics
- Vol. 59 (1) , 19-33
Universal Method of Searching for Equilibria and Stochastic Equilibria in Transportation Networks
A universal method of searching for usual and stochastic equilibria in congestion population games is proposed. The Beckmann and stable dynamics models of an equilibrium flow distribution...
- Open Access
Algorithmic models of human behavior and stochastic optimization
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 that characterized by unobservable convex function $f(x)$. Each day we can observe only the stochastic gradient of $f(x)$ (with heavy tails). We want to know where is a minimum of $f(x)$. What is better to live one long live or to live in parallel many short lives? The second problem is a variant of the previous one (we'd like to find the minimum of convex function $f(x)$) but we can observe only the (noise) value of the function at each day. The additional difficulties here is $f(x)$ isn't necessarily smooth and $x$ belongs to unit simplex. The third problem is to interprete equillibrium in Stable dynamic traffic assignment model (Nesterov-dePalma, 2000) as atractor of the best response dynamic. All these problems required proper generalizations of mirror descent (MD) algorithm. In this paper we collect different special versions of MD to solve the described problems.Open AccessAlgorithmic models of human behavior and stochastic optimization
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 that characterized by unobservable convex function $f(x)$. Each day we can observe only the stochastic gradient of $f(x)$ (with heavy tails). We want to know where is a minimum of $f(x)$. What is better to live one long live or to live in parallel many short lives? The second problem is a variant of the previous one (we'd like to find the minimum of convex function $f(x)$) but we can observe only the (noise) value of the function at each day. The additional difficulties here is $f(x)$ isn't necessarily smooth and $x$ belongs to unit simplex. The third problem is to interprete equillibrium in Stable dynamic traffic assignment model (Nesterov-dePalma, 2000) as atractor of the best response dynamic. All these problems required proper generalizations of mirror descent (MD) algorithm. In this paper we collect different special versions of MD to solve the described problems. - Open Access
Gradient-free two-points optimal method for non smooth stochastic convex optimization problem with additional small noise
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-smooth stochastic convex programming. We investigate how much can be the level of noise (the nature of this noise isn't necessary stochastic) for the rate of convergence to be maintained (up to a multiplicative factor).
Open AccessGradient-free two-points optimal method for non smooth stochastic convex optimization problem with additional small noise
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-smooth stochastic convex programming. We investigate how much can be the level of noise (the nature of this noise isn't necessary stochastic) for the rate of convergence to be maintained (up to a multiplicative factor).
- Open Access
Nonlinear stochastic multiarmed bandit problems with inexact oracle
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 the value (realization) of the function at one point or at two points. We allow these values to be inexact, but the level of noise should be small enough. We generalize well known results for inexact oracle case. And we also generalize classical results to prox-structures differ from euclidian.
Open AccessNonlinear stochastic multiarmed bandit problems with inexact oracle
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 the value (realization) of the function at one point or at two points. We allow these values to be inexact, but the level of noise should be small enough. We generalize well known results for inexact oracle case. And we also generalize classical results to prox-structures differ from euclidian.
- Open Access
Parallel algorithms and probability of large deviation for stochastic optimization problems
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 objective function is available, one can obtain, in parallel, several independent approximate solutions in terms of the objective residual expectation. Then, choosing the solution with the minimum function value, one can control the probability of large deviation of the objective residual. On the contrary, in this short paper, we address the situation, when the value of the objective function is unavailable or is too expensive to calculate. Under "`light-tail"' assumption for stochastic subgradient and in general case with moderate large deviation probability, we show that parallelization combined with averaging gives bounds for probability of large deviation similar to a serial method. Thus, in these cases, one can benefit from parallel computations and reduce the computational time without loss in the solution quality.
Open AccessParallel algorithms and probability of large deviation for stochastic optimization problems
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 objective function is available, one can obtain, in parallel, several independent approximate solutions in terms of the objective residual expectation. Then, choosing the solution with the minimum function value, one can control the probability of large deviation of the objective residual. On the contrary, in this short paper, we address the situation, when the value of the objective function is unavailable or is too expensive to calculate. Under "`light-tail"' assumption for stochastic subgradient and in general case with moderate large deviation probability, we show that parallelization combined with averaging gives bounds for probability of large deviation similar to a serial method. Thus, in these cases, one can benefit from parallel computations and reduce the computational time without loss in the solution quality.