Generalization Error Bounds for Kernel Matrix Completion and Extrapolation

Pere Gimenez-Febrer; Alba Pages-Zamora; Georgios B. Giannakis

doi:10.1109/LSP.2020.2970306

Generalization Error Bounds for Kernel Matrix Completion and Extrapolation

Pere Gimenez-Febrer
, Alba Pages-Zamora
, Georgios B. Giannakis

Electrical and Computer Engineering

Research output: Contribution to journal › Article › peer-review

8 Scopus citations

Abstract

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.

Original language	English (US)
Article number	8974415
Pages (from-to)	326-330
Number of pages	5
Journal	IEEE Signal Processing Letters
Volume	27
DOIs	https://doi.org/10.1109/LSP.2020.2970306
State	Published - 2020

Bibliographical note

Publisher Copyright:
© 1994-2012 IEEE.

Keywords

Matrix completion
Rademacher complexity
generalization error
kernel regression

Publisher link

10.1109/LSP.2020.2970306

Find It

Find It at U of M Libraries

Cite this

@article{138506ee4d17495ba27b2d242e90e359,

title = "Generalization Error Bounds for Kernel Matrix Completion and Extrapolation",

abstract = "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, Rademacher complexity, generalization error, kernel regression",

author = "Pere Gimenez-Febrer and Alba Pages-Zamora and Giannakis, \{Georgios B.\}",

note = "Publisher Copyright: {\textcopyright} 1994-2012 IEEE.",

year = "2020",

doi = "10.1109/LSP.2020.2970306",

language = "English (US)",

volume = "27",

pages = "326--330",

journal = "IEEE Signal Processing Letters",

issn = "1070-9908",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - JOUR

T1 - Generalization Error Bounds for Kernel Matrix Completion and Extrapolation

AU - Gimenez-Febrer, Pere

AU - Pages-Zamora, Alba

AU - Giannakis, Georgios B.

PY - 2020

Y1 - 2020

N2 - 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.

AB - 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.

KW - Matrix completion

KW - Rademacher complexity

KW - generalization error

KW - kernel regression

UR - https://www.scopus.com/pages/publications/85082170389

UR - https://www.scopus.com/pages/publications/85082170389#tab=citedBy

U2 - 10.1109/LSP.2020.2970306

DO - 10.1109/LSP.2020.2970306

M3 - Article

AN - SCOPUS:85082170389

SN - 1070-9908

VL - 27

SP - 326

EP - 330

JO - IEEE Signal Processing Letters

JF - IEEE Signal Processing Letters

M1 - 8974415

ER -

Generalization Error Bounds for Kernel Matrix Completion and Extrapolation

Abstract

Bibliographical note

Keywords

Publisher link

Find It

Other files and links

Fingerprint

Cite this