• Corpus ID: 3165097

Adaptive Stratified Sampling for Monte-Carlo integration of Differentiable functions

@inproceedings{Carpentier2012AdaptiveSS,
  title={Adaptive Stratified Sampling for Monte-Carlo integration of Differentiable functions},
  author={Alexandra Carpentier and R{\'e}mi Munos},
  booktitle={NIPS},
  year={2012}
}
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… 

Figures and Tables from this paper

Toward Optimal Stratification for Stratified Monte-Carlo Integration

An algorithm is provided that selects online, among a large class of partitions, the partition that provides the optimal trade-off, and allocates the samples almost optimally on this partition.

Approximate Function Evaluation via Multi-Armed Bandits

This work designs an instance-adaptive algorithm that learns to sample according to the importance of each coordinate, and with probability at least 1 − δ returns an ε accurate estimate of f ( µ ).

Adaptive Monte Carlo via Bandit Allocation

It is shown that well developed allocation strategies can be used to achieve an MSE that approaches that of the best estimator chosen in retrospect, and a new set of adaptive Monte Carlo strategies are developed that provide stronger guarantees than previous approaches while offering practical advantages.

Sampling-Based Uncertainty Quantification: Monte Carlo and Beyond

This chapter covers sampling methods beginning with Monte Carlo sampling and before proceeding to more sophisticated sampling procedures. In Sect. 7.1 the basic Monte Carlo methods are detailed and

Learning Multiple Markov Chains via Adaptive Allocation

A novel learning algorithm is presented that efficiently balances exploration and exploitation intrinsic to this problem, without any prior knowledge of the chains, and it is shown that the algorithm asymptotically attains an optimal loss.

M ay 2 01 9 Learning Multiple Markov Chains via Adaptive Allocation

A novel learning algorithm is presented that efficiently balances exploration and exploitation intrinsic to this problem, without any prior knowledge of the chains, and it is shown that the algorithm asymptotically attains an optimal loss.

Reliability analysis of shell truss structure by hybrid Monte Carlo method

The paper presents an example of reliability analysis of shell structures susceptible to stability loss from the condition of node snapping, which assumes the use of Neural Networks in Monte Carlo (MC) simulations to analyze the reliability of the structure.

References

SHOWING 1-10 OF 10 REFERENCES

Adaptive Optimal Allocation in Stratified Sampling Methods

In this paper, we propose a stratified sampling algorithm in which the random drawings made in the strata to compute the expectation of interest are also used to adaptively modify the proportion of

Empirical Bernstein Bounds and Sample-Variance Penalization

Improved constants for data dependent and variance sensitive confidence bounds are given, called empirical Bernstein bounds, and extended to hold uniformly over classes of functions whose growth function is polynomial in the sample size n, and sample variance penalization is considered.

Simulation and the Monte Carlo Method (Wiley Series in Probability and Statistics)

The authoritative resource for understanding the power behind Monte Carlo Methods and a new co-author has been added to enliven the writing style and to provide modern day expertise on new topics.

Simulation and the Monte Carlo method

  • R. Rubinstein
  • Physics
    Wiley series in probability and mathematical statistics
  • 1981
From the Publisher: Provides the first simultaneous coverage of the statistical aspects of simulation and Monte Carlo methods, their commonalities and their differences for the solution of a wide

Exploration-exploitation tradeoff using variance estimates in multi-armed bandits

Monte Carlo Methods in Financial Engineering

This paper presents a meta-modelling procedure that automates the very labor-intensive and therefore time-heavy and therefore expensive and expensive process of manually computing random numbers and random Variables.

Quasi-Monte Carlo methods and pseudo-random numbers

CONTENTS

Adaptive Stratified Sampling for Monte-Carlo integration of Differentiable functions

  • Technical report,
  • 2012

Finite Time Analysis of Stratified Sampling for Monte Carlo

This work proposes a strategy that samples the arms according to an upper bound on their standard deviations and compares its estimation quality to an ideal allocation that would know the standard deviations of the strata.

Active learning and its application to heteroscedastic problems

  • Department of Computing Science, Univ. of Alberta, MSc thesis,
  • 2009