Learning to Simulate: Generative Metamodeling via Quantile Regression

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Hong, L. Jeff, Hou, Yanxi, Zhang, Qingkai, Zhang, Xiaowei
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911385130106880
author Hong, L. Jeff
Hou, Yanxi
Zhang, Qingkai
Zhang, Xiaowei
author_facet Hong, L. Jeff
Hou, Yanxi
Zhang, Qingkai
Zhang, Xiaowei
contents Stochastic simulation models effectively capture complex system dynamics but are often too slow for real-time decision-making. Traditional metamodeling techniques learn relationships between simulator inputs and a single output summary statistic, such as the mean or median. These techniques enable real-time predictions without additional simulations. However, they require prior selection of one appropriate output summary statistic, limiting their flexibility in practical applications. We propose a new concept: generative metamodeling. It aims to construct a "fast simulator of the simulator," generating random outputs significantly faster than the original simulator while preserving approximately equal conditional distributions. Generative metamodels enable rapid generation of numerous random outputs upon input specification, facilitating immediate computation of any summary statistic for real-time decision-making. We introduce a new algorithm, quantile-regression-based generative metamodeling (QRGMM), and establish its distributional convergence and convergence rate. Extensive numerical experiments demonstrate QRGMM's efficacy compared to other state-of-the-art generative algorithms in practical real-time decision-making scenarios.
format Preprint
id arxiv_https___arxiv_org_abs_2311_17797
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Learning to Simulate: Generative Metamodeling via Quantile Regression
Hong, L. Jeff
Hou, Yanxi
Zhang, Qingkai
Zhang, Xiaowei
Machine Learning
Methodology
Stochastic simulation models effectively capture complex system dynamics but are often too slow for real-time decision-making. Traditional metamodeling techniques learn relationships between simulator inputs and a single output summary statistic, such as the mean or median. These techniques enable real-time predictions without additional simulations. However, they require prior selection of one appropriate output summary statistic, limiting their flexibility in practical applications. We propose a new concept: generative metamodeling. It aims to construct a "fast simulator of the simulator," generating random outputs significantly faster than the original simulator while preserving approximately equal conditional distributions. Generative metamodels enable rapid generation of numerous random outputs upon input specification, facilitating immediate computation of any summary statistic for real-time decision-making. We introduce a new algorithm, quantile-regression-based generative metamodeling (QRGMM), and establish its distributional convergence and convergence rate. Extensive numerical experiments demonstrate QRGMM's efficacy compared to other state-of-the-art generative algorithms in practical real-time decision-making scenarios.
title Learning to Simulate: Generative Metamodeling via Quantile Regression
topic Machine Learning
Methodology
url https://arxiv.org/abs/2311.17797