Sparse Signal Recovery via Rescaled Matching Pursuit von Li, Wan, Ye, Peixin

Volltext

The learning performance of the weak rescaled pure greedy algorithms von Guo, Qin, Liu, Xianghua, Ye, Peixin

Volltext

A multi-point collaborative DDoS defense mechanism for IIoT environment von Huang, Hongcheng, Ye, Peixin, Hu, Min, Wu, Jun

Volltext

Efficiency of orthogonal super greedy algorithm under the restricted isometry property von Wei, Xiujie, Ye, Peixin

Volltext

Silicon based integrated photonic chip technology for datacenter optical interconnection von Ye, Peixin

Volltext

Efficiency of Orthogonal Matching Pursuit for Group Sparse Recovery von Shao, Chunfang, Wei, Xiujie, Ye, Peixin, Xing, Shuo

Volltext

Approximation by the Extended Neural Network Operators of Kantorovich Type von Xiang, Chenghao, Zhao, Yi, Wang, Xu, Ye, Peixin

Volltext

Approximation Properties of the Vector Weak Rescaled Pure Greedy Algorithm von Xu, Xu, Guo, Jinyu, Ye, Peixin, Zhang, Wenhui

Volltext

Optimality of the Approximation and Learning by the Rescaled Pure Super Greedy Algorithms von Zhang, Wenhui, Ye, Peixin, Xing, Shuo, Xu, Xu

Volltext

Lebesgue constants for Chebyshev thresholding greedy algorithms von Shao, Chunfang, Ye, Peixin

Volltext

Convergence rate for the moving least-squares learning with dependent sampling von Guo, Qin, Ye, Peixin

Volltext

Error Analysis of Least-Squares l^} -Regularized Regression Learning Algorithm With the Non-Identical and Dependent Samples von Guo, Qin, Ye, Peixin

Volltext

Almost Optimality of the Orthogonal Super Greedy Algorithm for μ-Coherent Dictionaries von Shao, Chunfang, Chang, Jincai, Ye, Peixin, Zhang, Wenhui, Xing, Shuo

Volltext

Efficiency of weak greedy algorithms for m-term approximations von Ye, PeiXin, Wei, XiuJie

Volltext

Convergence Rate for l^ -Coefficient Regularized Regression With Non-i.i.d. Sampling von Guo, Qin, Ye, Peixin, Cai, Binlei

Volltext

The Learning Rates of Regularized Regression Based on Reproducing Kernel Banach Spaces von Sheng, Baohuai, Ye, Peixin

Volltext

QUANTUM COMPLEXITY OF SOBOLEV IMBEDDINGS von 叶培新

Volltext

Strong Convex Loss Can Increase the Learning Rates of Online Learning von Sheng, Baohuai, Duan, Liqin, Ye, Peixin

Volltext

Uniform Bounds of Aliasing and Truncated Errors in Sampling Series of Functions from Anisotropic Besov Class von Ye, Peixin, Han, Yongjie

Volltext

Error analysis for lq-coefficient regularized moving least-square regression von Guo, Qin, Ye, Peixin

Volltext