Juncai He

activity

20182026

most citedReLU Deep Neural Networks and Linear Finite Elements

155 citations · 379 across the 24 of their papers we have counts for

collaborators

Showing 2026Show all

3 papers · 1 filter

math.NA2026

Sharp Sobolev Sandwich and Approximation Rates of Radon-Domain $L^{p}$ Ridge Integral Spaces for ReLU $^{k}$ Networks

Juncai He, Zitong Tian

We develop the $L^{p}$ space and approximation theory for shallow neural networks with $ReLU^{k}$ activations. The central object is the Radon-domain $L^{p}$ space $\mathcal{R}L…

cs.LG2026

Neural Flow Operators can Approximate any Operator: Abstract Frameworks and Universal Approximations

Shuang Chen, Juncai He, Xue-Cheng Tai

We introduce an abstract neural flow framework for neural networks and neural operators. The framework contains two continuous-depth models, namely neural flows with composition an…

math.NA2026

Divergence-free Linearized Neural Networks: Integral Representation and Optimal Approximation Rates

Juncai He, Xinliang Liu, Zitong Tian

This paper studies the numerical approximation of divergence-free vector fields by linearized shallow neural networks, also referred to as random feature models or finite neuron sp…

Sharp Sobolev Sandwich and Approximation Rates of Radon-Domain Lp Ridge Integral Spaces for ReLUk Networks

Neural Flow Operators can Approximate any Operator: Abstract Frameworks and Universal Approximations

Divergence-free Linearized Neural Networks: Integral Representation and Optimal Approximation Rates

Sharp Sobolev Sandwich and Approximation Rates of Radon-Domain $L^{p}$ Ridge Integral Spaces for ReLU $^{k}$ Networks