This dissertation is dedicated to a rigorous analysis of sequential global optimization algorithms. We consider the stochastic bandit model where an agent aim at finding the input of a given system optimizing the output. The function which links the input to the output is not explicit, the agent requests sequentially an oracle to evaluate the output for any input. This function is not supposed to be convex and may display many local optima. In this work we tackle the challenging case where the evaluations are expensive, which requires to design a careful selection of the input to evaluate. We study two different goals, either to maximize the sum of the rewards received at each iteration, or to maximize the best reward found so far. The pres...
International audienceWe study the problem of global maximization of a function f given a finite num...
This discussion paper considers the use of stochastic algorithms for solving global optimisation pro...
Combinatorial stochastic semi-bandits appear naturally in many contexts where the exploration/exploi...
Cette thèse se consacre à une analyse rigoureuse des algorithmes d'optimisation globale équentielle....
This thesis deals with the problem of global optimization of expensive-to-evaluate functions in a Ba...
This work addresses the sequential optimization of an unknown and potentially nonconvex function ove...
In this thesis we study several machine learning problems that are all linked with the minimization ...
Real world systems often have parameterized controllers which can be tuned to improve performance. B...
In this thesis, we study three classes of problems within the general area of sequential decision ma...
This document presents in a unified way different results about the optimal solution of several mult...
Cette thèse est consacrée à l'étude théorique et numérique d'algorithmes d'optimisation stochastique...
This thesis is focused on the convergence analysis of some popular stochastic approximation methods ...
Abstract. We consider the problem of optimizing a real-valued con-tinuous function f, which is suppo...
International audienceWe consider function optimization as a sequential decision making problem unde...
International audienceWe consider the problem of optimizing a real-valued continuous function f, whi...
International audienceWe study the problem of global maximization of a function f given a finite num...
This discussion paper considers the use of stochastic algorithms for solving global optimisation pro...
Combinatorial stochastic semi-bandits appear naturally in many contexts where the exploration/exploi...
Cette thèse se consacre à une analyse rigoureuse des algorithmes d'optimisation globale équentielle....
This thesis deals with the problem of global optimization of expensive-to-evaluate functions in a Ba...
This work addresses the sequential optimization of an unknown and potentially nonconvex function ove...
In this thesis we study several machine learning problems that are all linked with the minimization ...
Real world systems often have parameterized controllers which can be tuned to improve performance. B...
In this thesis, we study three classes of problems within the general area of sequential decision ma...
This document presents in a unified way different results about the optimal solution of several mult...
Cette thèse est consacrée à l'étude théorique et numérique d'algorithmes d'optimisation stochastique...
This thesis is focused on the convergence analysis of some popular stochastic approximation methods ...
Abstract. We consider the problem of optimizing a real-valued con-tinuous function f, which is suppo...
International audienceWe consider function optimization as a sequential decision making problem unde...
International audienceWe consider the problem of optimizing a real-valued continuous function f, whi...
International audienceWe study the problem of global maximization of a function f given a finite num...
This discussion paper considers the use of stochastic algorithms for solving global optimisation pro...
Combinatorial stochastic semi-bandits appear naturally in many contexts where the exploration/exploi...