Zhi-Qin John Xu

List of research outcomes

This list is not complete and representing at the moment only items from zbMATH Open and arXiv. We are working on additional sources - please check back here soon!

Publication	Date of Publication	Type
Solving multiscale dynamical systems by deep learning (available as arXiv preprint)	N/A	Paper
Loss Jump During Loss Switch in Solving PDEs with Neural Networks (available as arXiv preprint)	N/A	Paper
A rationale from a frequency perspective for grokking in training neural networks Communications in Computational Physics	2026-09-15	Paper
Anchor function: a type of benchmark functions for studying language models Journal of Machine Learning	2026-09-01	Paper
A first-principles theory of slow thinking and active perception Journal of Machine Learning	2026-09-01	Paper
A deep learning approach for solving the inverse problem of the wave equation CSIAM Transactions on Applied Mathematics	2026-04-29	Paper
Solving multiscale dynamical systems by deep learning Computer Physics Communications	2025-10-15	Paper
Optimistic estimate uncovers the potential of nonlinear models Journal of Machine Learning	2025-10-07	Paper
Phase diagram of initial condensation for two-layer neural networks CSIAM Transactions on Applied Mathematics	2025-09-17	Paper
Embedding principle in depth for the loss landscape analysis of deep neural networks CSIAM Transactions on Applied Mathematics	2025-09-17	Paper
Implicit bias in understanding deep learning for solving PDEs beyond Ritz-Galerkin method CSIAM Transactions on Applied Mathematics	2025-09-17	Paper
Theory of the frequency principle for general deep neural networks CSIAM Transactions on Applied Mathematics	2025-08-19	Paper
Understanding the initial condensation of convolutional neural networks CSIAM Transactions on Applied Mathematics	2025-08-05	Paper
Overview frequency principle/spectral bias in deep learning Communications on Applied Mathematics and Computation	2025-07-24	Paper
Embedding principle: a hierarchical structure of loss landscape of deep neural networks Journal of Machine Learning	2025-07-22	Paper
On understanding and overcoming spectral biases of deep neural network learning methods for solving PDEs Journal of Computational Physics	2025-05-14	Paper
Input gradient annealing neural network for solving Fokker-Planck equations with low temperature Journal of Computational Physics	2025-03-05	Paper
Loss jump during loss switch in solving PDEs with neural networks Communications in Computational Physics	2024-12-02	Paper
Laplace-fPINNs: Laplace-based fractional physics-informed neural networks for solving forward and inverse problems of a time fractional equation East Asian Journal on Applied Mathematics	2024-10-31	Paper
Bayesian inversion with neural operator (BINO) for modeling subdiffusion: forward and inverse problems Journal of Computational and Applied Mathematics	2024-08-26	Paper
An Unsupervised Deep Learning Approach for the Wave Equation Inverse Problem	2023-11-08	Paper
A Correction and Comments on “Multi-Scale Deep Neural Network (MscaleDNN) for Solving Poisson-Boltzmann Equation in Complex Domains CiCP, 28(5):1970–2001,2020” Communications in Computational Physics	2023-07-06	Paper
Subspace decomposition based DNN algorithm for elliptic type multi-scale PDEs Journal of Computational Physics	2023-06-16	Paper
Laplace-fPINNs: Laplace-based fractional physics-informed neural networks for solving forward and inverse problems of subdiffusion	2023-04-03	Paper
On the Exact Computation of Linear Frequency Principle Dynamics and Its Generalization SIAM Journal on Mathematics of Data Science	2022-11-23	Paper
Bayesian Inversion with Neural Operator (BINO) for Modeling Subdiffusion: Forward and Inverse Problems	2022-11-21	Paper
MOD-Net: a machine learning approach via model-operator-data network for solving PDEs Communications in Computational Physics	2022-09-16	Paper
Frequency Principle: Fourier Analysis Sheds Light on Deep Neural Networks Communications in Computational Physics	2021-11-02	Paper
A multi-scale DNN algorithm for nonlinear elliptic equations with multiple scales Communications in Computational Physics	2021-11-02	Paper
Multi-scale deep neural network (MscaleDNN) for solving Poisson-Boltzmann equation in complex domains Communications in Computational Physics	2021-11-02	Paper
Phase diagram for two-layer ReLU neural networks at infinite-width limit (available as arXiv preprint)	2021-07-09	Paper
Phase diagram for two-layer ReLU neural networks at infinite-width limit	2021-07-09	Paper
Fourier-domain Variational Formulation and Its Well-posedness for Supervised Learning	2020-12-06	Paper
Implicit bias with Ritz-Galerkin method in understanding deep learning for solving PDEs	2020-02-18	Paper
A dynamical state underlying the second order maximum entropy principle in neuronal networks Communications in Mathematical Sciences	2017-05-30	Paper

Research outcomes over time

This page was built for person: Zhi-Qin John Xu