A novel unconstrained optimization model named weighted trace-penalty
mi...
Both classical Fourier transform-based methods and neural network method...
Spectral methods which represent data points by eigenvectors of kernel
m...
This paper proves the global convergence of a triangularized
orthogonali...
In this work, we analyze the global convergence property of coordinate
g...
We introduce a data distribution scheme for ℋ-matrices and a
distributed...
A novel orthogonalization-free method together with two specific algorit...
Structured CNN designed using the prior information of problems potentia...
We consider universal approximations of symmetric and anti-symmetric
fun...
Recent advancements in conditional Generative Adversarial Networks (cGAN...
In this work, we study the tensor ring decomposition and its associated
...
A novel solve-training framework is proposed to train neural network in
...
Deep networks, especially Convolutional Neural Networks (CNNs), have bee...
Low-rank approximations are popular methods to reduce the high computati...
Low-rank approximations are popular techniques to reduce the high
comput...
This paper proposes an efficient method for computing selected generaliz...
The hierarchical interpolative factorization (HIF) offers an efficient w...
Kernel matrices are popular in machine learning and scientific computing...