AI RESEARCH

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

arXiv CS.LG

ArXi:2508.15198v2 Announce Type: replace Tensor neural networks (TNNs) have nstrated 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