
Neural Network Approximation: Three Hidden Layers Are Enough
A threehiddenlayer neural network with super approximation power is in...
read it

Structure Probing Neural Network Deflation
Deep learning is a powerful tool for solving nonlinear differential equa...
read it

TwoLayer Neural Networks for Partial Differential Equations: Optimization and Generalization Theory
Deep learning has significantly revolutionized the design of numerical a...
read it

Deep Network Approximation with Discrepancy Being Reciprocal of Width to Power of Depth
A new network with super approximation power is introduced. This network...
read it

Rapid Application of the Spherical Harmonic Transform via Interpolative Decomposition Butterfly Factorization
We describe an algorithm for the application of the forward and inverse ...
read it

SelectNet: Selfpaced Learning for Highdimensional Partial Differential Equations
The residual method with deep neural networks as function parametrizatio...
read it

Deep Network Approximation for Smooth Functions
This paper establishes optimal approximation error characterization of d...
read it

Machine Learning for Prediction with Missing Dynamics
This article presents a general framework for recovering missing dynamic...
read it

IntDeep: A Deep Learning Initialized Iterative Method for Nonlinear Problems
This paper focuses on proposing a deep learning initialized iterative me...
read it

Multidimensional Phase Recovery and Interpolative Decomposition Butterfly Factorization
This paper focuses on the fast evaluation of the matvec g=Kf for K∈C^N× ...
read it

Instance Enhancement Batch Normalization: an Adaptive Regulator of Batch Noise
Batch Normalization (BN) (Ioffe and Szegedy 2015) normalizes the feature...
read it

Error bounds for deep ReLU networks using the KolmogorovArnold superposition theorem
We prove a theorem concerning the approximation of multivariate continuo...
read it

Deep Network Approximation Characterized by Number of Neurons
This paper quantitatively characterizes the approximation power of deep ...
read it

DIANet: DenseandImplicit Attention Network
Attentionbased deep neural networks (DNNs) that emphasize the informati...
read it

CASS: Cross Adversarial Source Separation via Autoencoder
This paper introduces a cross adversarial source separation (CASS) frame...
read it

SelectNet: Learning to Sample from the Wild for Imbalanced Data Training
Supervised learning from training data with imbalanced class sizes, a co...
read it

Nonlinear Approximation via Compositions
We study the approximation efficiency of function compositions in nonlin...
read it

DropActivation: Implicit Parameter Reduction and Harmonic Regularization
Overfitting frequently occurs in deep learning. In this paper, we propos...
read it

NonOscillatory Pattern Learning for NonStationary Signals
This paper proposes a novel nonoscillatory pattern (NOP) learning schem...
read it

Interior Eigensolver for Sparse Hermitian Definite Matrices Based on Zolotarev's Functions
This paper proposes an efficient method for computing selected generaliz...
read it

Recursive DiffeomorphismBased Regression for Shape Functions
This paper proposes a recursive diffeomorphism based regression method f...
read it
Haizhao Yang
is this you? claim profile