activity
20242026
collaborators

12 papers

math.NA2026

Optimal Neural Network Approximation via Empirical Least Squares with Deterministic Samples

Xinliang Liu, Tong Mao, Jinchao Xu

We develop a rigorous theory of discrete residual least-squares approximation for elliptic spectral equations using linearized ReLU neural networks on the sp…

cs.LG2026

Do Neural Networks Really Beat the Curse of Dimensionality? A Bit-Complexity View

Tong Mao, Jinchao Xu

Traditional approximation theory measures convergence rates in terms of the number of parameters or degrees of freedom. However, practical computation operates under finite precisi…

math.NA2026

McMg: A Learned Phase-Space Multi-channel Multigrid Preconditioner for Helmholtz Equation

Jiwei Jia, Xinliang Liu, Juntao Wang +1

Solving heterogeneous Helmholtz equations at high wavenumbers remains challenging because the discretized operator is indefinite, pollution degrades phase accuracy, and scalar coar…

cs.LG2026

On the Dimension-Free Approximation of Deep Neural Networks for Symmetric Korobov Functions

Yulong Lu, Tong Mao, Jinchao Xu +1

Deep neural networks have been widely used as universal approximators for functions with inherent physical structures, including permutation symmetry. In this paper, we construct s…

math.NA2026

Solving High-Dimensional PDEs Using Linearized Neural Networks

Tong Mao, Jinchao Xu, Xiaofeng Xu

Linearized shallow neural networks that are constructed by fixing the hidden-layer parameters have recently shown strong performance in solving partial differential equations (PDEs…

math.NA2025

Condition Numbers and Eigenvalue Spectra of Shallow Networks on Spheres

Xinliang Liu, Tong Mao, Jinchao Xu

We present an estimation of the condition numbers of the \emph{mass} and \emph{stiffness} matrices arising from shallow ReLU neural networks defined on the unit sphere~$\mathbb…