Evolution Strategies (ESs) are population-based methods well suited for parallelization. In this report, we study the convergence of the (mu/mu_w,lambda)-ES, an ES with weighted recombination, and derive its optimal convergence rate and optimal mu especially for large population sizes. First, we theoretically prove the log-linear convergence of the algorithm using a scale-invariant adaptation rule for the step-size and minimizing spherical objective functions and identify its convergence rate as the expectation of an underlying random variable. Then, using Monte-Carlo computations of the convergence rate in the case of equal weights, we derive optimal values for mu that we compare with previously proposed rules. Our numerical computations s...
This thesis aims to improve statistical methods suitable for stochastic models of population genetic...
Cette thèse étudie la méthode du gradient conjugué et la méthode de Lanczos pour la résolution de pr...
Approximate Value Iteration (AVI) is a method for solving a large Markov Decision Problem by approxi...
International audienceEvolution Strategies (ESs) are population-based methods well suited for parall...
Evolution Strategies (ESs) are population-based methods well suited for parallelization. In this rep...
International audienceIn this paper, we investigate the effect of a learning rate for the mean in Ev...
An adapted version is published in SIAM Journal on Financial MathematicsWe analyze the robustness pr...
Cette thèse est consacrée à l'étude des propriétés de convergence forte du schéma de Ninomiya et Vic...
This thesis investigates the conjugate-gradient method and the Lanczos method for the solution of un...
Evolution Strategies (ES) are stochastic derivative-free optimization algorithms whose most prominen...
International audienceThe CSA-ES is an Evolution Strategy with Cumulative Step size Adaptation, wher...
Derivative-free optimization (DFO) has enjoyed renewed interest over the past years, mostly motivate...
International audienceThis paper presents a refined single parent evolution strategy that is derando...
This paper is concerned with the links between the Value Iteration algorithm and the Rolling Horizon...
International audienceMarkov chain Monte Carlo (MCMC) methods together with hidden Markov models are...
This thesis aims to improve statistical methods suitable for stochastic models of population genetic...
Cette thèse étudie la méthode du gradient conjugué et la méthode de Lanczos pour la résolution de pr...
Approximate Value Iteration (AVI) is a method for solving a large Markov Decision Problem by approxi...
International audienceEvolution Strategies (ESs) are population-based methods well suited for parall...
Evolution Strategies (ESs) are population-based methods well suited for parallelization. In this rep...
International audienceIn this paper, we investigate the effect of a learning rate for the mean in Ev...
An adapted version is published in SIAM Journal on Financial MathematicsWe analyze the robustness pr...
Cette thèse est consacrée à l'étude des propriétés de convergence forte du schéma de Ninomiya et Vic...
This thesis investigates the conjugate-gradient method and the Lanczos method for the solution of un...
Evolution Strategies (ES) are stochastic derivative-free optimization algorithms whose most prominen...
International audienceThe CSA-ES is an Evolution Strategy with Cumulative Step size Adaptation, wher...
Derivative-free optimization (DFO) has enjoyed renewed interest over the past years, mostly motivate...
International audienceThis paper presents a refined single parent evolution strategy that is derando...
This paper is concerned with the links between the Value Iteration algorithm and the Rolling Horizon...
International audienceMarkov chain Monte Carlo (MCMC) methods together with hidden Markov models are...
This thesis aims to improve statistical methods suitable for stochastic models of population genetic...
Cette thèse étudie la méthode du gradient conjugué et la méthode de Lanczos pour la résolution de pr...
Approximate Value Iteration (AVI) is a method for solving a large Markov Decision Problem by approxi...