Adaptive Stratified Sampling for Monte-Carlo integration of Differentiable functions

A. Carpentier 1 R. Munos 1
1 SEQUEL - Sequential Learning
LIFL - Laboratoire d'Informatique Fondamentale de Lille, LAGIS - Laboratoire d'Automatique, Génie Informatique et Signal, Inria Lille - Nord Europe
Abstract : We consider the problem of adaptive stratified sampling for Monte Carlo integration of a differentiable function given a finite number of evaluations to the function. We construct a sampling scheme that samples more often in regions where the function oscillates more, while allocating the samples such that they are well spread on the domain (this notion shares similitude with low discrepancy). We prove that the estimate returned by the algorithm is almost similarly accurate as the estimate that an optimal oracle strategy (that would know the variations of the function \textiteverywhere) would return, and provide a finite-sample analysis.
Type de document :
Communication dans un congrès
Advances in Neural Information Processing Systems, 2012, Lake Tahoe, United States. 2012
Liste complète des métadonnées

https://hal.inria.fr/hal-00943123
Contributeur : Philippe Preux <>
Soumis le : vendredi 7 février 2014 - 08:23:59
Dernière modification le : jeudi 11 janvier 2018 - 06:22:13

Identifiants

  • HAL Id : hal-00943123, version 1

Collections

Citation

A. Carpentier, R. Munos. Adaptive Stratified Sampling for Monte-Carlo integration of Differentiable functions. Advances in Neural Information Processing Systems, 2012, Lake Tahoe, United States. 2012. 〈hal-00943123〉

Partager

Métriques

Consultations de la notice

139