Generalization error bounds for kernel matrix completion and extrapolation

Pere Gimenez Febrer, Alba Pages-Zamora, Georgios B. Giannakis
2020 IEEE Signal Processing Letters  
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. P. Giménez-Febrer and A. Pagès-Zamora are with the
doi:10.1109/lsp.2020.2970306 fatcat:aghbyn2ourh2tgycyrg7tip4fi