Pengzhan Jin

Orcid: 0000-0002-2169-1491

According to our database1, Pengzhan Jin authored at least 17 papers between 2019 and 2024.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

On csauthors.net:

Bibliography

2024
Shallow ReLU neural networks and finite elements.
CoRR, 2024

Learning solution operators of PDEs defined on varying domains via MIONet.
CoRR, 2024

A hybrid iterative method based on MIONet for PDEs: Theory and numerical examples.
CoRR, 2024

2023
Learning Poisson Systems and Trajectories of Autonomous Systems via Poisson Neural Networks.
IEEE Trans. Neural Networks Learn. Syst., November, 2023

Experimental observation on a low-rank tensor model for eigenvalue problems.
CoRR, 2023

2022
MIONet: Learning Multiple-Input Operators via Tensor Product.
SIAM J. Sci. Comput., 2022

Approximation capabilities of measure-preserving neural networks.
Neural Networks, 2022

Tensor Neural Network and Its Numerical Integration.
CoRR, 2022

On Numerical Integration in Neural Ordinary Differential Equations.
Proceedings of the International Conference on Machine Learning, 2022

2021
Learning nonlinear operators via DeepONet based on the universal approximation theorem of operators.
Nat. Mach. Intell., 2021

2020
Unit Triangular Factorization of the Matrix Symplectic Group.
SIAM J. Matrix Anal. Appl., 2020

SympNets: Intrinsic structure-preserving symplectic networks for identifying Hamiltonian systems.
Neural Networks, 2020

Quantifying the generalization error in deep learning in terms of data distribution and neural network smoothness.
Neural Networks, 2020

Inverse modified differential equations for discovery of dynamics.
CoRR, 2020

Deep Hamiltonian networks based on symplectic integrators.
CoRR, 2020

Symplectic networks: Intrinsic structure-preserving networks for identifying Hamiltonian systems.
CoRR, 2020

2019
DeepONet: Learning nonlinear operators for identifying differential equations based on the universal approximation theorem of operators.
CoRR, 2019


  Loading...