Uncertainty in Artificial Intelligence
First Name   Last Name   Password   Forgot Password   Log in!
    Proceedings         Authors   Author's Info   Article details         Search    
A variational approach to stable principal component pursuit
Aleksandr Aravkin, Stephen Becker, Volkan Cevher, Peder Olsen
Abstract:
We introduce a new convex formulation for stable principal component pursuit (SPCP) to decompose noisy signals into low-rank and sparse representations. For numerical solu- tions of our SPCP formulation, we first de- velop a convex variational framework and then accelerate it with quasi-Newton meth- ods. We show, via synthetic and real data experiments, that our approach offers advan- tages over the classical SPCP formulations in scalability and practical parameter selection.
Keywords:
Pages: 32-41
PS Link:
PDF Link: /papers/14/p32-aravkin.pdf
BibTex:
@INPROCEEDINGS{Aravkin14,
AUTHOR = "Aleksandr Aravkin and Stephen Becker and Volkan Cevher and Peder Olsen",
TITLE = "A variational approach to stable principal component pursuit",
BOOKTITLE = "Proceedings of the Thirtieth Conference Annual Conference on Uncertainty in Artificial Intelligence (UAI-14)",
PUBLISHER = "AUAI Press",
ADDRESS = "Corvallis, Oregon",
YEAR = "2014",
PAGES = "32--41"
}


hosted by DSL   •   site info   •   help