arXiv Machine Learning By Yulun Wu, Miguel Aguiar, Karl H. Johansson, Matthieu Barreau

Iterative Training of Physics-Informed Neural Networks with Fourier-enhanced Features

Read the original on arXiv Machine Learning →

arXiv:2510. 19399v2 Announce Type: replace Abstract: Spectral bias, the tendency of neural networks to learn low-frequency features first, is a well-known issue with many training algorithms for physics-informed neural networks (PINNs).

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

Hugging Face Trending Papers
Aug 6

Alternating Levenberg-Marquardt Training of Physics-Informed Neural Networks with Fourier-Enhanced Features

Physics-informed neural networks (PINNs) often fail to accurately resolve partial differential equations (PDEs) with high-frequency or multi-scale solutions, as well as strongly nonlinear problems. Two factors underlie this difficulty: spectral bias, the tendency of neural networks to underfit high-frequency features; and representation-coefficient coupling, the entanglement of representation learning and coefficient fitting within a single nonconvex optimization objective.

arXiv Machine Learning
Jul 3

Fourier Preconditioning for Neural Feature Learning

arXiv:2607. 02199v1 Announce Type: cross Abstract: Mutual information (MI)-inspired feature learning techniques are capable of generating low-dimensional embeddings that retain nonlinear dependence structures, but direct estimations of MI suffer from noisy probability distribution estimates in the low-data regime.

By Preston Pitzer, Anish Pradhan, Harpreet S. Dhillon