Hyper-Reduced Autoencoders for Efficient and Accurate Nonlinear Model Reductions
Abstract
Projection-based model order reduction on nonlinear manifolds has been recently proposed for problems with slowly decaying Kolmogorov n-width such as advection-dominated ones. These methods often use neural networks for manifold learning and showcase improved accuracy over traditional linear subspace-reduced order models. A disadvantage of the previously proposed methods is the potential high computational costs of training the networks on high-fidelity solution snapshots. In this work, we propose and analyze a novel method that overcomes this disadvantage by training a neural network only on subsampled versions of the high-fidelity solution snapshots. This method coupled with collocation-based hyper-reduction and Gappy-POD allows for efficient and accurate surrogate models. We demonstrate the validity of our approach on a 2d Burgers problem.
Cite
@article{arxiv.2303.09630,
title = {Hyper-Reduced Autoencoders for Efficient and Accurate Nonlinear Model Reductions},
author = {Jorio Cocola and John Tencer and Francesco Rizzi and Eric Parish and Patrick Blonigan},
journal= {arXiv preprint arXiv:2303.09630},
year = {2023}
}