Generalization error bounds for kernel matrix completion and extrapolation

Autor:	Giménez-Febrer, Pere, Pagès-Zamora, Alba, Giannakis, Georgios B.
Rok vydání:	2019
Předmět:	Statistics - Machine Learning Computer Science - Machine Learning
Druh dokumentu:	Working Paper
DOI:	10.1109/LSP.2020.2970306
Popis:	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.
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/1906.08770 Zobrazit plný text záznamu View this record from Arxiv