Stochastic spectral embedding


METADATA ONLY
Loading...

Date

2021

Publication Type

Journal Article

ETH Bibliography

yes

Citations

Altmetric
METADATA ONLY

Data

Rights / License

Abstract

Constructing approximations that can accurately mimic the behavior of complex models at reduced computational costs is an important aspect of uncertainty quantification. Despite their flexibility and efficiency, classical surrogate models such as kriging or polynomial chaos expansions tend to struggle with highly nonlinear, localized, or nonstationary computational models. We hereby propose a novel sequential adaptive surrogate modeling method based on recursively embedding locally spectral expansions. It is achieved by means of disjoint recursive partitioning of the input domain, which consists in sequentially splitting the latter into smaller subdomains, and constructing simpler local spectral expansions in each, exploiting the trade-off complexity vs. locality. The resulting expansion, which we refer to as "stochastic spectral embedding" (SSE), is a piecewise continuous approximation of the model response that shows promising approximation capabilities, and good scaling with both the problem dimension and the size of the training set. We finally show how the method compares favorably against state-of-the-art sparse polynomial chaos expansions on a set of models with different complexity and input dimension. © 2021 by Begell House, Inc.

Permanent link

Publication status

published

Editor

Book title

Volume

11 (2)

Pages / Article No.

25 - 47

Publisher

Begell House

Event

Edition / version

Methods

Software

Geographic location

Date collected

Date created

Subject

Stochastic spectral embedding; Surrogate modeling; Spectral expansions; Sparse regression; Uncertainty quantification

Organisational unit

03962 - Sudret, Bruno / Sudret, Bruno check_circle

Notes

Funding

Related publications and datasets