.png){kind=icon}
.png){kind=icon}
Return
Generalization Error Bounds for Kernel Matrix Completion and Extrapolation
.png){kind=icon}
OA
AI
DOI：10.1109/LSP.2020.2970306.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Prior information can be incorporated in matrix completion to improve estimation accuracy and extrapolate the missing entries. Reproducing kernel Hilbert spaces provide tools to leverage the said prior information, and derive more reliable algorithms. This paper analyzes the generalization error of such approaches, and presents numerical tests confirming the theoretical results.
Keywords:
Matrix completion
kernel regression
generalization error
Rademacher complexity
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
9.6
Papers:
1.1W
Citations:
1.7W