Sample Average Approximation with Adaptive Importance Sampling

Andreas Waechter, Jeremy C Staum, Alvaro Maggiar, Mingbin Feng

Research output: Book/ReportOther report

Abstract

We study sample average approximations under adaptive importance sampling in which the sample densities may depend on previous random samples. Based on a generic uniform law of large numbers, we establish uniform convergence of the sample average approximation to the true function. We obtain convergence of the optimal value and optimal solutions of the sample average approximation. The relevance of this result is demonstrated in the context of the convergence analysis of a randomized optimization algorithm.

Available at optimization-online.org
Original languageEnglish (US)
Number of pages13
StatePublished - 2017

Fingerprint

Sample Average Approximation
Adaptive Sampling
Importance Sampling
Uniform Law of Large numbers
Online Optimization
Randomized Algorithms
Uniform convergence
Convergence Analysis
Optimization Algorithm
Optimal Solution

Cite this

Waechter, Andreas ; Staum, Jeremy C ; Maggiar, Alvaro ; Feng, Mingbin. / Sample Average Approximation with Adaptive Importance Sampling. 2017. 13 p.
@book{19a8956d12e845f5b46c031852b0c41c,
title = "Sample Average Approximation with Adaptive Importance Sampling",
abstract = "We study sample average approximations under adaptive importance sampling in which the sample densities may depend on previous random samples. Based on a generic uniform law of large numbers, we establish uniform convergence of the sample average approximation to the true function. We obtain convergence of the optimal value and optimal solutions of the sample average approximation. The relevance of this result is demonstrated in the context of the convergence analysis of a randomized optimization algorithm.Available at optimization-online.org",
author = "Andreas Waechter and Staum, {Jeremy C} and Alvaro Maggiar and Mingbin Feng",
note = "http://www.optimization-online.org/DB_FILE/2017/04/5951.pdf",
year = "2017",
language = "English (US)",

}

Sample Average Approximation with Adaptive Importance Sampling. / Waechter, Andreas; Staum, Jeremy C; Maggiar, Alvaro; Feng, Mingbin.

2017. 13 p.

Research output: Book/ReportOther report

TY - BOOK

T1 - Sample Average Approximation with Adaptive Importance Sampling

AU - Waechter, Andreas

AU - Staum, Jeremy C

AU - Maggiar, Alvaro

AU - Feng, Mingbin

N1 - http://www.optimization-online.org/DB_FILE/2017/04/5951.pdf

PY - 2017

Y1 - 2017

N2 - We study sample average approximations under adaptive importance sampling in which the sample densities may depend on previous random samples. Based on a generic uniform law of large numbers, we establish uniform convergence of the sample average approximation to the true function. We obtain convergence of the optimal value and optimal solutions of the sample average approximation. The relevance of this result is demonstrated in the context of the convergence analysis of a randomized optimization algorithm.Available at optimization-online.org

AB - We study sample average approximations under adaptive importance sampling in which the sample densities may depend on previous random samples. Based on a generic uniform law of large numbers, we establish uniform convergence of the sample average approximation to the true function. We obtain convergence of the optimal value and optimal solutions of the sample average approximation. The relevance of this result is demonstrated in the context of the convergence analysis of a randomized optimization algorithm.Available at optimization-online.org

M3 - Other report

BT - Sample Average Approximation with Adaptive Importance Sampling

ER -