collaborators

5 papers

math.NA2026

A Multi-Level Machine Learning Framework for Inverse Scattering Problems with Multi-Frequency Data

Yi Liu, Yanzhao Cao, Junshan Lin +1

In this work, we propose a multi-level machine learning framework for solving inverse scattering problems with multi-frequency data. The multi-level neural network is built along t…

cs.LG2026

Fourier Multi-Component and Multi-Layer Neural Networks: Unlocking High-Frequency Potential

Shijun Zhang, Hongkai Zhao, Yimin Zhong +1

The architecture of a neural network and the choice of its activation function are both fundamental to its performance. Equally important is ensuring that these two elements are we…

cs.LG2025

Structured and Balanced Multi-Component and Multi-Layer Neural Networks

Shijun Zhang, Hongkai Zhao, Yimin Zhong +1

In this work, we propose a balanced multi-component and multi-layer neural network (MMNN) structure to accurately and efficiently approximate functions with complex features, in te…

cs.LG2025

Why Shallow Networks Struggle to Approximate and Learn High Frequencies

Shijun Zhang, Hongkai Zhao, Yimin Zhong +1

In this work, we present a comprehensive study combining mathematical and computational analysis to explain why a two-layer neural network struggles to handle high frequencies in b…

math.AP2025

Transport models for wave propagation in scattering media with nonlinear absorption

Joseph Kraisler, Wei Li, Kui Ren +2

This work considers the propagation of high-frequency waves in highly-scattering media where physical absorption of a nonlinear nature occurs. Using the classical tools of the Wign…