Finite-Time Analysis of Stratified Sampling for Monte Carlo - Archive ouverte HAL Access content directly
Conference Papers Year : 2011

## Finite-Time Analysis of Stratified Sampling for Monte Carlo

(1) , (1)
1
Alexandra Carpentier
• Function : Author
• PersonId : 910455
Rémi Munos
• Function : Author
• PersonId : 836863

#### Abstract

We consider the problem of stratified sampling for Monte-Carlo integration. We model this problem in a multi-armed bandit setting, where the arms represent the strata, and the goal is to estimate a weighted average of the mean values of the arms. We propose a strategy that samples the arms according to an upper bound on their standard deviations and compare its estimation quality to an ideal allocation that would know the standard deviations of the strata. We provide two regret analyses: a distribution-dependent bound $\widetilde O(n^{-3/2})$ that depends on a measure of the disparity of the strata, and a distribution-free bound $\widetilde O(n^{-4/3})$ that does not.

#### Domains

Statistics [stat] Other Statistics [stat.ML]

### Dates and versions

inria-00636924 , version 1 (28-10-2011)
inria-00636924 , version 2 (13-01-2012)
inria-00636924 , version 3 (27-02-2012)

### Identifiers

• HAL Id : inria-00636924 , version 3

### Cite

Alexandra Carpentier, Rémi Munos. Finite-Time Analysis of Stratified Sampling for Monte Carlo. NIPS - Twenty-Fifth Annual Conference on Neural Information Processing Systems, Dec 2011, Grenade, Spain. ⟨inria-00636924v3⟩

### Export

BibTeX TEI Dublin Core DC Terms EndNote Datacite

218 View