Zhi-Qin John Xu

Orcid: 0000-0003-0627-3520

Affiliations:

Shanghai Jiao Tong University, School of Mathematical Sciences, Shanghai, China

According to our database¹, Zhi-Qin John Xu authored at least 53 papers between 2018 and 2024.

Collaborative distances:

Dijkstra number² of four.
Erdős number³ of four.

Timeline

Legend:

Book

In proceedings

Article

PhD thesis

Dataset

Other

Bibliography

2024

Understanding Time Series Anomaly State Detection through One-Class Classification.

[BibT_eX]

[DOI]

CoRR, 2024

Anchor function: a type of benchmark functions for studying language models.

[BibT_eX]

[DOI]

CoRR, 2024

Solving multiscale dynamical systems by deep learning.

[BibT_eX]

[DOI]

CoRR, 2024

2023

<i>DeepFlame</i>: A deep learning empowered open-source platform for reacting flow simulations.

[BibT_eX]

[DOI]

Comput. Phys. Commun., October, 2023

Subspace decomposition based DNN algorithm for elliptic type multi-scale PDEs.

[BibT_eX]

[DOI]

Xi-An Li

Zhi-Qin John Xu

Lei Zhang

J. Comput. Phys., September, 2023

An Unsupervised Deep Learning Approach for the Wave Equation Inverse Problem.

[BibT_eX]

[DOI]

CoRR, 2023

Optimistic Estimate Uncovers the Potential of Nonlinear Models.

[BibT_eX]

[DOI]

CoRR, 2023

Solving a class of multi-scale elliptic PDEs by means of Fourier-based mixed physics informed neural networks.

[BibT_eX]

[DOI]

CoRR, 2023

Stochastic Modified Equations and Dynamics of Dropout Algorithm.

[BibT_eX]

[DOI]

CoRR, 2023

Loss Spike in Training Neural Networks.

[BibT_eX]

[DOI]

Zhongwang Zhang

Zhi-Qin John Xu

CoRR, 2023

Understanding the Initial Condensation of Convolutional Neural Networks.

[BibT_eX]

[DOI]

CoRR, 2023

Laplace-fPINNs: Laplace-based fractional physics-informed neural networks for solving forward and inverse problems of subdiffusion.

[BibT_eX]

[DOI]

Xiong-bin Yan

Zhi-Qin John Xu

Zheng Ma

CoRR, 2023

Phase Diagram of Initial Condensation for Two-layer Neural Networks.

[BibT_eX]

[DOI]

CoRR, 2023

2022

On the Exact Computation of Linear Frequency Principle Dynamics and Its Generalization.

[BibT_eX]

[DOI]

SIAM J. Math. Data Sci., 2022

A regularised deep matrix factorised model of matrix completion for image restoration.

[BibT_eX]

[DOI]

IET Image Process., 2022

Bayesian Inversion with Neural Operator (BINO) for Modeling Subdiffusion: Forward and Inverse Problems.

[BibT_eX]

[DOI]

Xiong-bin Yan

Zhi-Qin John Xu

Zheng Ma

CoRR, 2022

Linear Stability Hypothesis and Rank Stratification for Nonlinear Models.

[BibT_eX]

[DOI]

CoRR, 2022

Implicit regularization of dropout.

[BibT_eX]

[DOI]

Zhongwang Zhang

Zhi-Qin John Xu

CoRR, 2022

Embedding Principle in Depth for the Loss Landscape Analysis of Deep Neural Networks.

[BibT_eX]

[DOI]

CoRR, 2022

An Experimental Comparison Between Temporal Difference and Residual Gradient with Neural Network Approximation.

[BibT_eX]

[DOI]

CoRR, 2022

Limitation of characterizing implicit regularization by data-independent functions.

[BibT_eX]

[DOI]

CoRR, 2022

Overview frequency principle/spectral bias in deep learning.

[BibT_eX]

[DOI]

Zhi-Qin John Xu

Yaoyu Zhang

Tao Luo

CoRR, 2022

A multi-scale sampling method for accurate and robust deep neural network to predict combustion chemical kinetics.

[BibT_eX]

[DOI]

CoRR, 2022

A deep learning-based model reduction (DeePMR) method for simplifying chemical kinetics.

[BibT_eX]

[DOI]

CoRR, 2022

Towards Understanding the Condensation of Neural Networks at Initial Training.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Empirical Phase Diagram for Three-layer Neural Networks with Infinite Width.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

An Upper Limit of Decaying Rate with Respect to Frequency in Linear Frequency Principle Model.

[BibT_eX]

[DOI]

Proceedings of the Mathematical and Scientific Machine Learning, 2022

2021

Phase Diagram for Two-layer ReLU Neural Networks at Infinite-width Limit.

[BibT_eX]

[DOI]

J. Mach. Learn. Res., 2021

Embedding Principle: a hierarchical structure of loss landscape of deep neural networks.

[BibT_eX]

[DOI]

CoRR, 2021

A variance principle explains why dropout finds flatter minima.

[BibT_eX]

[DOI]

Zhongwang Zhang

Hanxu Zhou

Zhi-Qin John Xu

CoRR, 2021

Data-informed Deep Optimization.

[BibT_eX]

[DOI]

Lulu Zhang

Zhi-Qin John Xu

Yaoyu Zhang

CoRR, 2021

Force-in-domain GAN inversion.

[BibT_eX]

[DOI]

Guangjie Leng

Yekun Zhu

Zhi-Qin John Xu

CoRR, 2021

MOD-Net: A Machine Learning Approach via Model-Operator-Data Network for Solving PDEs.

[BibT_eX]

[DOI]

CoRR, 2021

Towards Understanding the Condensation of Two-layer Neural Networks at Initial Training.

[BibT_eX]

[DOI]

CoRR, 2021

An Upper Limit of Decaying Rate with Respect to Frequency in Deep Neural Network.

[BibT_eX]

[DOI]

CoRR, 2021

Linear Frequency Principle Model to Understand the Absence of Overfitting in Neural Networks.

[BibT_eX]

[DOI]

CoRR, 2021

Frequency Principle in Deep Learning Beyond Gradient-descent-based Training.

[BibT_eX]

[DOI]

Yuheng Ma

Zhi-Qin John Xu

Jiwei Zhang

CoRR, 2021

Embedding Principle of Loss Landscape of Deep Neural Networks.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Deep Frequency Principle Towards Understanding Why Deeper Learning Is Faster.

[BibT_eX]

[DOI]

Zhiqin John Xu

Hanxu Zhou

Proceedings of the Thirty-Fifth AAAI Conference on Artificial Intelligence, 2021

2020

Fourier-domain Variational Formulation and Its Well-posedness for Supervised Learning.

[BibT_eX]

[DOI]

CoRR, 2020

A regularized deep matrix factorized model of matrix completion for image restoration.

[BibT_eX]

[DOI]

CoRR, 2020

Multi-scale Deep Neural Network (MscaleDNN) for Solving Poisson-Boltzmann Equation in Complex Domains.

[BibT_eX]

[DOI]

Ziqi Liu

Wei Cai

Zhi-Qin John Xu

CoRR, 2020

Implicit bias with Ritz-Galerkin method in understanding deep learning for solving PDEs.

[BibT_eX]

[DOI]

CoRR, 2020

A type of generalization error induced by initialization in deep neural networks.

[BibT_eX]

[DOI]

Proceedings of Mathematical and Scientific Machine Learning, 2020

2019

Dynamical and Coupling Structure of Pulse-Coupled Networks in Maximum Entropy Analysis.

[BibT_eX]

[DOI]

Zhi-Qin John Xu

Douglas Zhou

David Cai

Entropy, 2019

Multi-scale Deep Neural Networks for Solving High Dimensional PDEs.

[BibT_eX]

[DOI]

Wei Cai

Zhi-Qin John Xu

CoRR, 2019

Theory of the Frequency Principle for General Deep Neural Networks.

[BibT_eX]

[DOI]

CoRR, 2019

Explicitizing an Implicit Bias of the Frequency Principle in Two-layer Neural Networks.

[BibT_eX]

[DOI]

CoRR, 2019

Frequency Principle: Fourier Analysis Sheds Light on Deep Neural Networks.

[BibT_eX]

[DOI]

CoRR, 2019

Training Behavior of Deep Neural Network in Frequency Domain.

[BibT_eX]

[DOI]

Zhi-Qin John Xu

Yaoyu Zhang

Yanyang Xiao

Proceedings of the Neural Information Processing - 26th International Conference, 2019

2018

Frequency Principle in Deep Learning with General Loss Functions and Its Potential Application.

[BibT_eX]

[DOI]

Zhi-Qin John Xu

CoRR, 2018

Maximum Entropy Principle Analysis in Network Systems with Short-time Recordings.

[BibT_eX]

[DOI]

CoRR, 2018

Understanding training and generalization in deep learning by Fourier analysis.

[BibT_eX]

[DOI]

Zhiqin John Xu

CoRR, 2018

Zhi-Qin John Xu

Timeline

Legend:

Links

Online presence:

On csauthors.net:

Bibliography

Loading...