Leveraging time and parameters for nonlinear model reduction methods

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Glas, Silke, Unger, Benjamin
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929663799984128
author Glas, Silke
Unger, Benjamin
author_facet Glas, Silke
Unger, Benjamin
contents In this paper, we consider model order reduction (MOR) methods for problems with slowly decaying Kolmogorov $n$-widths as, e.g., certain wave-like or transport-dominated problems. To overcome this Kolmogorov barrier within MOR, nonlinear projections are used, which are often realized numerically using autoencoders. These autoencoders generally consist of a nonlinear encoder and a nonlinear decoder and involve costly training of the hyperparameters to obtain a good approximation quality of the reduced system. To facilitate the training process, we show that extending the to-be-reduced system and its corresponding training data makes it possible to replace the nonlinear encoder with a linear encoder without sacrificing accuracy, thus roughly halving the number of hyperparameters to be trained.
format Preprint
id arxiv_https___arxiv_org_abs_2501_03853
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Leveraging time and parameters for nonlinear model reduction methods
Glas, Silke
Unger, Benjamin
Numerical Analysis
Machine Learning
In this paper, we consider model order reduction (MOR) methods for problems with slowly decaying Kolmogorov $n$-widths as, e.g., certain wave-like or transport-dominated problems. To overcome this Kolmogorov barrier within MOR, nonlinear projections are used, which are often realized numerically using autoencoders. These autoencoders generally consist of a nonlinear encoder and a nonlinear decoder and involve costly training of the hyperparameters to obtain a good approximation quality of the reduced system. To facilitate the training process, we show that extending the to-be-reduced system and its corresponding training data makes it possible to replace the nonlinear encoder with a linear encoder without sacrificing accuracy, thus roughly halving the number of hyperparameters to be trained.
title Leveraging time and parameters for nonlinear model reduction methods
topic Numerical Analysis
Machine Learning
url https://arxiv.org/abs/2501.03853