32 citations · 125 across the 21 of their papers we have counts for
22 papers
Recovering Linear Causal Models with Latent Variables via Cholesky Factorization of Covariance Matrix
Yunfeng Cai, Xu Li, Minging Sun +1
Discovering the causal relationship via recovering the directed acyclic graph (DAG) structure from the observed data is a well-known challenging combinatorial problem. When there a…
S3IM: Stochastic Structural SIMilarity and Its Unreasonable Effectiveness for Neural Fields
Zeke Xie, Xindi Yang, Yujie Yang +5
Recently, Neural Radiance Field (NeRF) has shown great success in rendering novel-view images of a given scene by learning an implicit representation with only posed RGB images. Ne…
Convergence analysis of a block preconditioned steepest descent eigensolver with implicit deflation
Ming Zhou, Zhaojun Bai, Yunfeng Cai +1
Gradient-type iterative methods for solving Hermitian eigenvalue problems can be accelerated by using preconditioning and deflation techniques. A preconditioned steepest descent it…
SpaceE: Knowledge Graph Embedding by Relational Linear Transformation in the Entity Space
Jinxing Yu, Yunfeng Cai, Mingming Sun +1
Translation distance based knowledge graph embedding (KGE) methods, such as TransE and RotatE, model the relation in knowledge graphs as translation or rotation in the vector space…
On the Power-Law Hessian Spectrums in Deep Learning
Zeke Xie, Qian-Yuan Tang, Yunfeng Cai +2
It is well-known that the Hessian of deep loss landscape matters to optimization, generalization, and even robustness of deep learning. Recent works empirically discovered that the…
S-MLPv2: Improved Spatial-Shift MLP Architecture for Vision
Tan Yu, Xu Li, Yunfeng Cai +2
Recently, MLP-based vision backbones emerge. MLP-based vision architectures with less inductive bias achieve competitive performance in image recognition compared with CNNs and vis…
Rethinking Token-Mixing MLP for MLP-based Vision Backbone
Tan Yu, Xu Li, Yunfeng Cai +2
In the past decade, we have witnessed rapid progress in the machine vision backbone. By introducing the inductive bias from the image processing, convolution neural network (CNN) h…
S-MLP: Spatial-Shift MLP Architecture for Vision
Tan Yu, Xu Li, Yunfeng Cai +2
Recently, visual Transformer (ViT) and its following works abandon the convolution and exploit the self-attention operation, attaining a comparable or even higher accuracy than CNN…
Identification of Matrix Joint Block Diagonalization
Yunfeng Cai, Ping Li
Given a set of square matrices, the matrix blind joint block diagonalization problem (BJBDP) is to find a full column rank matrix such that $C_i=A…
Tensor Completion via Tensor Networks with a Tucker Wrapper
Yunfeng Cai, Ping Li
In recent years, low-rank tensor completion (LRTC) has received considerable attention due to its applications in image/video inpainting, hyperspectral data recovery, etc. With dif…
Magnetic Noise Enabled Biocompass
Da-Wu Xiao, Wen-Hui Hu, Yunfeng Cai +1
The discovery of magnetic protein provides a new understanding of a biocompass at the molecular level. However, the mechanism by which magnetic protein enables a biocompass is stil…
Solving the Robust Matrix Completion Problem via a System of Nonlinear Equations
Yunfeng Cai, Ping Li
We consider the problem of robust matrix completion, which aims to recover a low rank matrix and a sparse matrix from incomplete observations of their sum $M=L_*+S_*\in…
An Inverse-free Truncated Rayleigh-Ritz Method for Sparse Generalized Eigenvalue Problem
Yunfeng Cai, Ping Li
This paper considers the sparse generalized eigenvalue problem (SGEP), which aims to find the leading eigenvector with at most nonzero entries. SGEP naturally arises in many ap…
Advanced Variations of Two-Dimensional Principal Component Analysis for Face Recognition
Meixiang Zhao, Zhigang Jia, Yunfeng Cai +2
The two-dimensional principal component analysis (2DPCA) has become one of the most powerful tools of artificial intelligent algorithms. In this paper, we review 2DPCA and its vari…
Relaxed 2-D Principal Component Analysis by Norm for Face Recognition
Xiao Chen, Zhi-Gang Jia, Yunfeng Cai +1
A relaxed two dimensional principal component analysis (R2DPCA) approach is proposed for face recognition. Different to the 2DPCA, 2DPCA- and G2DPCA, the R2DPCA utilizes the l…
Perturbation Analysis of An Eigenvector-Dependent Nonlinear Eigenvalue Problem With Applications?
Yunfeng Cai, Zhigang Jia, Zheng-Jian Bai
The eigenvector-dependent nonlinear eigenvalue problem (NEPv) , where the columns of are orthonormal, , is Hermitia…
Solving General Joint Block Diagonalization Problem via Linearly Independent Eigenvectors of a Matrix Polynomial
Yunfeng Cai, Guanghui Cheng, Decai Shi
In this paper, we consider the exact/approximate general joint block diagonalization (GJBD) problem of a matrix set (), where a nonsingular matrix (of…
Perturbation Analysis for Matrix Joint Block Diagonalization
Yunfeng Cai, Reng-cang Li
The matrix joint block diagonalization problem (JBDP) of a given matrix set is about finding a nonsingular matrix such that all are…
An Algebraic Approach to Non-Orthogonal General Joint Block Diagonalization
Yunfeng Cai, Chengyu Liu
The exact/approximate non-orthogonal general joint block diagonalization ({\sc nogjbd}) problem of a given real matrix set is to find a nonsingular ma…
On Some Inverse Eigenvalue Problems of Quadratic Palindromic Systems
Yunfeng Cai, Jiang Qian
This paper concerns some inverse eigenvalue problems of the quadratic -(anti)-palindromic system , where , $A_1, A_0 \in \mathbb{C…
Convergence analysis of a locally accelerated preconditioned steepest descent method for Hermitian-definite generalized eigenvalue problems
Yunfeng Cai, Zhaojun Bai, John E. Pask +1
By extending the classical analysis techniques due to Samokish, Faddeev and Faddeeva, and Longsine and McCormick among others, we prove the convergence of preconditioned steepest d…
Hybrid preconditioning for iterative diagonalization of ill-conditioned generalized eigenvalue problems in electronic structure calculations
Yunfeng Cai, Zhaojun Bai, John E. Pask +1
The iterative diagonalization of a sequence of large ill-conditioned generalized eigenvalue problems is a computational bottleneck in quantum mechanical methods employing a nonorth…