Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Podina, Lena, Rad, Mahdi Torabi, Kohandel, Mohammad
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2405.08111
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866929342277222400
author Podina, Lena
Rad, Mahdi Torabi
Kohandel, Mohammad
author_facet Podina, Lena
Rad, Mahdi Torabi
Kohandel, Mohammad
contents Physics-informed neural networks (PINNs) are an influential method of solving differential equations and estimating their parameters given data. However, since they make use of neural networks, they provide only a point estimate of differential equation parameters, as well as the solution at any given point, without any measure of uncertainty. Ensemble and Bayesian methods have been previously applied to quantify the uncertainty of PINNs, but these methods may require making strong assumptions on the data-generating process, and can be computationally expensive. Here, we introduce Conformalized PINNs (C-PINNs) that, without making any additional assumptions, utilize the framework of conformal prediction to quantify the uncertainty of PINNs by providing intervals that have finite-sample, distribution-free statistical validity.
format Preprint
id arxiv_https___arxiv_org_abs_2405_08111
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Conformalized Physics-Informed Neural Networks
Podina, Lena
Rad, Mahdi Torabi
Kohandel, Mohammad
Machine Learning
Physics-informed neural networks (PINNs) are an influential method of solving differential equations and estimating their parameters given data. However, since they make use of neural networks, they provide only a point estimate of differential equation parameters, as well as the solution at any given point, without any measure of uncertainty. Ensemble and Bayesian methods have been previously applied to quantify the uncertainty of PINNs, but these methods may require making strong assumptions on the data-generating process, and can be computationally expensive. Here, we introduce Conformalized PINNs (C-PINNs) that, without making any additional assumptions, utilize the framework of conformal prediction to quantify the uncertainty of PINNs by providing intervals that have finite-sample, distribution-free statistical validity.
title Conformalized Physics-Informed Neural Networks
topic Machine Learning
url https://arxiv.org/abs/2405.08111