The impact of different methods of gradient descent on the spectral bias of physics-informed neural networks

Bachelor Thesis (2025)
Author(s)

A.F. van den Arend Schmidt (TU Delft - Electrical Engineering, Mathematics and Computer Science)

Contributor(s)

J. Sun – Mentor (TU Delft - Pattern Recognition and Bioinformatics)

Alexander Heinlein – Mentor (TU Delft - Numerical Analysis)

T. Wang – Mentor

Hayley Hung – Graduation committee member (TU Delft - Pattern Recognition and Bioinformatics)

Faculty
Electrical Engineering, Mathematics and Computer Science
More Info
expand_more
Publication Year
2025
Language
English
Graduation Date
31-01-2025
Awarding Institution
Delft University of Technology
Project
['CSE3000 Research Project']
Programme
['Computer Science and Engineering']
Faculty
Electrical Engineering, Mathematics and Computer Science
Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Abstract

Physics-Informed Neural Networks (PINNs) are intended to solve complex problems that obey physical rules or laws but have noisy or little data. These problems are encountered in a wide range of fields including for instance bioengineering, fluid mechanics, meta-material design and high-dimensional partial differential equations (PDEs). Whilst PINNs show promising results, they often fail to converge in the presence of higher frequency components; a problem known as the spectral bias. Multiple studies have explored ways to overcome or minimize spectral bias specifically for PINNs. This paper builds on previous studies by investigating the impact of different gradient descent methods on the spectral bias.

Files

Final_Paper_RP.pdf
(pdf | 2.28 Mb)
License info not available