A unified linear convergence analysis of k-SVD

• Main Authors: Xu, Zhiqiang, Ke, Yiping, Cao, Xin, Zhou, Chunlai, Wei, Pengfei, Gao, Xin
• Other Authors: School of Computer Science and Engineering
• Format: Article
• Language: English
• Published: 2022
• Subjects: Science; Eigenvector Computation; k-SVD
• Online Access: https://hdl.handle.net/10356/155195
• Institution: Nanyang Technological University

Eigenvector computation, e.g., k-SVD for finding top-k singular subspaces, is often of central importance to many scientific and engineering tasks. There has been resurgent interest recently in analyzing relevant methods in terms of singular value gap dependence. Particularly, when the gap vanishes,...