Skip to main content

LOw-rank data modeling via the minimum description length principle

Publication ,  Journal Article
Ramírez, I; Sapiro, G
Published in: ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
October 23, 2012

Robust low-rank matrix estimation is a topic of increasing interest, with promising applications in a variety of fields, from computer vision to data mining and recommender systems. Recent theoretical results establish the ability of such data models to recover the true underlying low-rank matrix when a large portion of the measured matrix is either missing or arbitrarily corrupted. However, if low rank is not a hypothesis about the true nature of the data, but a device for extracting regularity from it, no current guidelines exist for choosing the rank of the estimated matrix. In this work we address this problem by means of the Minimum Description Length (MDL) principle - a well established information-theoretic approach to statistical inference - as a guideline for selecting a model for the data at hand. We demonstrate the practical usefulness of our formal approach with results for complex background extraction in video sequences. © 2012 IEEE.

Duke Scholars

Published In

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

DOI

ISSN

1520-6149

Publication Date

October 23, 2012

Start / End Page

2165 / 2168
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Ramírez, I., & Sapiro, G. (2012). LOw-rank data modeling via the minimum description length principle. ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, 2165–2168. https://doi.org/10.1109/ICASSP.2012.6288341
Ramírez, I., and G. Sapiro. “LOw-rank data modeling via the minimum description length principle.” ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, October 23, 2012, 2165–68. https://doi.org/10.1109/ICASSP.2012.6288341.
Ramírez I, Sapiro G. LOw-rank data modeling via the minimum description length principle. ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. 2012 Oct 23;2165–8.
Ramírez, I., and G. Sapiro. “LOw-rank data modeling via the minimum description length principle.” ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, Oct. 2012, pp. 2165–68. Scopus, doi:10.1109/ICASSP.2012.6288341.
Ramírez I, Sapiro G. LOw-rank data modeling via the minimum description length principle. ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. 2012 Oct 23;2165–2168.

Published In

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

DOI

ISSN

1520-6149

Publication Date

October 23, 2012

Start / End Page

2165 / 2168