A unified linear convergence analysis of k-SVD

• المؤلفون الرئيسيون: Xu, Zhiqiang, Ke, Yiping, Cao, Xin, Zhou, Chunlai, Wei, Pengfei, Gao, Xin
• مؤلفون آخرون: School of Computer Science and Engineering
• التنسيق: مقال
• اللغة: English
• منشور في: 2022
• الموضوعات: Science; Eigenvector Computation; k-SVD
• الوصول للمادة أونلاين: https://hdl.handle.net/10356/155195

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,...