Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Gao, Yuan, Lang, Quanjun, Lu, Fei
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2412.03506
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866912760480137216
author Gao, Yuan
Lang, Quanjun
Lu, Fei
author_facet Gao, Yuan
Lang, Quanjun
Lu, Fei
contents The construction of loss functions presents a major challenge in data-driven modeling involving weak-form operators in PDEs and gradient flows, particularly due to the need to select test functions appropriately. We address this challenge by introducing self-test loss functions, which employ test functions that depend on the unknown parameters, specifically for cases where the operator depends linearly on the unknowns. The proposed self-test loss function conserves energy for gradient flows and coincides with the expected log-likelihood ratio for stochastic differential equations. Importantly, it is quadratic, facilitating theoretical analysis of identifiability and well-posedness of the inverse problem, while also leading to efficient parametric or nonparametric regression algorithms. It is computationally simple, requiring only low-order derivatives or even being entirely derivative-free, and numerical experiments demonstrate its robustness against noisy and discrete data.
format Preprint
id arxiv_https___arxiv_org_abs_2412_03506
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Self-test loss functions for learning weak-form operators and gradient flows
Gao, Yuan
Lang, Quanjun
Lu, Fei
Machine Learning
The construction of loss functions presents a major challenge in data-driven modeling involving weak-form operators in PDEs and gradient flows, particularly due to the need to select test functions appropriately. We address this challenge by introducing self-test loss functions, which employ test functions that depend on the unknown parameters, specifically for cases where the operator depends linearly on the unknowns. The proposed self-test loss function conserves energy for gradient flows and coincides with the expected log-likelihood ratio for stochastic differential equations. Importantly, it is quadratic, facilitating theoretical analysis of identifiability and well-posedness of the inverse problem, while also leading to efficient parametric or nonparametric regression algorithms. It is computationally simple, requiring only low-order derivatives or even being entirely derivative-free, and numerical experiments demonstrate its robustness against noisy and discrete data.
title Self-test loss functions for learning weak-form operators and gradient flows
topic Machine Learning
url https://arxiv.org/abs/2412.03506