58 citations · 215 across the 23 of their papers we have counts for
23 papers
Tensor Completion via Tensor Train Based Low-Rank Quotient Geometry under a Preconditioned Metric
Jian-Feng Cai, Wen Huang, Haifeng Wang +1
This paper investigates the low-rank tensor completion problem, which is about recovering a tensor from partially observed entries. We consider this problem in the tensor train for…
Approximation Theory of Total Variation Minimization for Data Completion
Jian-Feng Cai, Jae Kyu Choi, Ke Wei
Total variation (TV) minimization is one of the most important techniques in modern signal/image processing, and has wide range of applications. While there are numerous recent wor…
An Inexact Riemannian Proximal Gradient Method
Wen Huang, Ke Wei
This paper considers the problem of minimizing the summation of a differentiable function and a nonsmooth function on a Riemannian manifold. In recent years, proximal gradient meth…
Is Attention Better Than Matrix Decomposition?
Zhengyang Geng, Meng-Hao Guo, Hongxu Chen +3
As an essential ingredient of modern deep learning, attention mechanism, especially self-attention, plays a vital role in the global correlation discovery. However, is hand-crafted…
Implicit Regularization and Entrywise Convergence of Riemannian Optimization for Low Tucker-Rank Tensor Completion
Haifeng Wang, Jinchi Chen, Ke Wei
This paper is concerned with the low Tucker-rank tensor completion problem, which is about reconstructing a tensor of low multilinear rank f…
Image Restoration: Structured Low Rank Matrix Framework for Piecewise Smooth Functions and Beyond
Jian-Feng Cai, Jae Kyu Choi, Jingyang Li +1
Recently, mapping a signal/image into a low rank Hankel/Toeplitz matrix has become an emerging alternative to the traditional sparse regularization, due to its ability to alleviate…