In this thesis we study iterative algorithms in order to solve constrained and unconstrained convex optimization problems, variational inequalities with monotone operators and saddle point problems. We study these problems when the dimension of the search space is high and when the values of the functions of interest are unknown and we just can deal with a stochastic oracle. The algorithms we study are stochastic adaptation of two algorithms : the first one is a variant of the mirror descent algorithm proposed by Nemirovski and Yudin and the second one a variant of the dual extrapolation algorithm by Nesterov. For both of them, we provide bounds for the expected value and bounds for moderate deviations of the approximation error with differ...
This dissertation investigates the use of sampling methods for solving stochastic optimization probl...
International audienceWe consider convex-concave saddle-point problems where the objective functions...
Le sujet de cette thèse est l'analyse de divers algorithmes stochastiques visant à résoudre un probl...
In this thesis we study iterative algorithms in order to solve constrained and unconstrained convex ...
L objet de cette thèse est l étude d algorithmes itératifs permettant de résoudre des problèmes d op...
Stochastic approximation (SA) methods, first proposed by Robbins and Monro in 1951 for root- findin...
In this thesis we investigate the design and complexity analysis of the algorithms to solve convex p...
In this thesis we investigate the design and complexity analysis of the algorithms to solve convex p...
In this thesis we study several machine learning problems that are all linked with the minimization ...
In this thesis we study several machine learning problems that are all linked with the minimization ...
The subject of this thesis is the analysis of several stochastic algorithms in a nonconvex setting. ...
In this thesis we study several machine learning problems that are all linked with the minimization ...
This dissertation investigates the use of sampling methods for solving stochastic optimization probl...
We consider stochastic variational inequalities (VIs) with monotone operators where the feasible set...
The subject of this thesis is the analysis of several stochastic algorithms in a nonconvex setting. ...
This dissertation investigates the use of sampling methods for solving stochastic optimization probl...
International audienceWe consider convex-concave saddle-point problems where the objective functions...
Le sujet de cette thèse est l'analyse de divers algorithmes stochastiques visant à résoudre un probl...
In this thesis we study iterative algorithms in order to solve constrained and unconstrained convex ...
L objet de cette thèse est l étude d algorithmes itératifs permettant de résoudre des problèmes d op...
Stochastic approximation (SA) methods, first proposed by Robbins and Monro in 1951 for root- findin...
In this thesis we investigate the design and complexity analysis of the algorithms to solve convex p...
In this thesis we investigate the design and complexity analysis of the algorithms to solve convex p...
In this thesis we study several machine learning problems that are all linked with the minimization ...
In this thesis we study several machine learning problems that are all linked with the minimization ...
The subject of this thesis is the analysis of several stochastic algorithms in a nonconvex setting. ...
In this thesis we study several machine learning problems that are all linked with the minimization ...
This dissertation investigates the use of sampling methods for solving stochastic optimization probl...
We consider stochastic variational inequalities (VIs) with monotone operators where the feasible set...
The subject of this thesis is the analysis of several stochastic algorithms in a nonconvex setting. ...
This dissertation investigates the use of sampling methods for solving stochastic optimization probl...
International audienceWe consider convex-concave saddle-point problems where the objective functions...
Le sujet de cette thèse est l'analyse de divers algorithmes stochastiques visant à résoudre un probl...