Frequency-adaptive tensor neural networks for high-dimensional multi-scale problems

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Huang, Jizu, Qiu, Yue, You, Rukang
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866917494863691776
author Huang, Jizu
Qiu, Yue
You, Rukang
author_facet Huang, Jizu
Qiu, Yue
You, Rukang
contents Tensor neural networks (TNNs) have demonstrated their superiority in solving high-dimensional problems. However, similar to conventional neural networks, TNNs are also influenced by the Frequency Principle, which limits their ability to accurately capture high-frequency features of the solution. In this work, we analyze the training dynamics of TNNs by Fourier analysis and enhance their expressivity for high-dimensional multi-scale problems by incorporating random Fourier features. Leveraging the inherent tensor structure of TNNs, we further propose a novel approach to extract frequency features of high-dimensional functions by performing the Discrete Fourier Transform to one-dimensional component functions. This strategy effectively mitigates the curse of dimensionality. Building on this idea, we propose a frequency-adaptive TNNs algorithm, which significantly improves the ability of TNNs in solving complex multi-scale problems. Extensive numerical experiments are performed to validate the effectiveness and robustness of the proposed frequency-adaptive TNNs algorithm.
format Preprint
id arxiv_https___arxiv_org_abs_2508_15198
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Frequency-adaptive tensor neural networks for high-dimensional multi-scale problems
Huang, Jizu
Qiu, Yue
You, Rukang
Machine Learning
Mathematical Physics
Tensor neural networks (TNNs) have demonstrated their superiority in solving high-dimensional problems. However, similar to conventional neural networks, TNNs are also influenced by the Frequency Principle, which limits their ability to accurately capture high-frequency features of the solution. In this work, we analyze the training dynamics of TNNs by Fourier analysis and enhance their expressivity for high-dimensional multi-scale problems by incorporating random Fourier features. Leveraging the inherent tensor structure of TNNs, we further propose a novel approach to extract frequency features of high-dimensional functions by performing the Discrete Fourier Transform to one-dimensional component functions. This strategy effectively mitigates the curse of dimensionality. Building on this idea, we propose a frequency-adaptive TNNs algorithm, which significantly improves the ability of TNNs in solving complex multi-scale problems. Extensive numerical experiments are performed to validate the effectiveness and robustness of the proposed frequency-adaptive TNNs algorithm.
title Frequency-adaptive tensor neural networks for high-dimensional multi-scale problems
topic Machine Learning
Mathematical Physics
url https://arxiv.org/abs/2508.15198