
Datainformed Deep Optimization
Complex design problems are common in the scientific and industrial fiel...
read it

Forceindomain GAN inversion
Empirical works suggest that various semantics emerge in the latent spac...
read it

MODNet: A Machine Learning Approach via ModelOperatorData Network for Solving PDEs
In this paper, we propose a modeloperatordata network (MODNet) for so...
read it

Embedding Principle of Loss Landscape of Deep Neural Networks
Understanding the structure of loss landscape of deep neural networks (D...
read it

Towards Understanding the Condensation of Twolayer Neural Networks at Initial Training
It is important to study what implicit regularization is imposed on the ...
read it

An Upper Limit of Decaying Rate with Respect to Frequency in Deep Neural Network
Deep neural network (DNN) usually learns the target function from low to...
read it

Linear Frequency Principle Model to Understand the Absence of Overfitting in Neural Networks
Why heavily parameterized neural networks (NNs) do not overfit the data ...
read it

Frequency Principle in Deep Learning Beyond Gradientdescentbased Training
Frequency perspective recently makes progress in understanding deep lear...
read it

Fourierdomain Variational Formulation and Its Wellposedness for Supervised Learning
A supervised learning problem is to find a function in a hypothesis func...
read it

On the exact computation of linear frequency principle dynamics and its generalization
Recent works show an intriguing phenomenon of Frequency Principle (FPri...
read it

A regularized deep matrix factorized model of matrix completion for image restoration
It has been an important approach of using matrix completion to perform ...
read it

Deep frequency principle towards understanding why deeper learning is faster
Understanding the effect of depth in deep learning is a critical problem...
read it

Multiscale Deep Neural Network (MscaleDNN) for Solving PoissonBoltzmann Equation in Complex Domains
In this paper, we propose novel multiscale DNNs (MscaleDNN) using the i...
read it

Phase diagram for twolayer ReLU neural networks at infinitewidth limit
How neural network behaves during the training over different choices of...
read it

Implicit bias with RitzGalerkin method in understanding deep learning for solving PDEs
This paper aims at studying the difference between RitzGalerkin (RG) m...
read it

A priori generalization error for twolayer ReLU neural network through minimum norm solution
We focus on estimating a priori generalization error of twolayer ReLU n...
read it

Multiscale Deep Neural Networks for Solving High Dimensional PDEs
In this paper, we propose the idea of radial scaling in frequency domain...
read it

Theory of the Frequency Principle for General Deep Neural Networks
Along with fruitful applications of Deep Neural Networks (DNNs) to reali...
read it

Explicitizing an Implicit Bias of the Frequency Principle in Twolayer Neural Networks
It remains a puzzle that why deep neural networks (DNNs), with more para...
read it

A type of generalization error induced by initialization in deep neural networks
How different initializations and loss functions affect the learning of ...
read it

Frequency Principle: Fourier Analysis Sheds Light on Deep Neural Networks
We study the training process of Deep Neural Networks (DNNs) from the Fo...
read it

Frequency Principle in Deep Learning with General Loss Functions and Its Potential Application
Previous studies have shown that deep neural networks (DNNs) with common...
read it

Swift Twosample Test on Highdimensional Neural Spiking Data
To understand how neural networks process information, it is important t...
read it

Maximum Entropy Principle Analysis in Network Systems with Shorttime Recordings
In many realistic systems, maximum entropy principle (MEP) analysis prov...
read it
ZhiQin John Xu
is this you? claim profile