[Ml-stat-talks] Emmanuel Candes in TODAY's colloquium at ORFE

Philippe Rigollet rigollet at Princeton.EDU
Tue Oct 23 09:37:30 EDT 2012

=== ORFE Colloquium Announcement ===

DATE:   Today, October 23, 2012

TIME:   4:30pm

LOCATION:   Room 101, Sherrerd Hall

SPEAKER:   Emmanuel Candès, Dept. of Mathematics & Dept. of Statistics, Stanford University

TITLE:   Robust Principal Component Analysis? Some Theory and Some Applications

ABSTRACT:  This talk is about a curious phenomenon. Suppose we have a data matrix, which is the superposition
of a low-rank component and a sparse component. Can we recover each component individually? We prove that
under some suitable assumptions, it is possible to recover both the low-rank and the sparse components exactly
by solving a very convenient convex program. This suggests the possibility of a principled approach to robust
principal component analysis since our methodology and results assert that one can recover the principal
components of a data matrix even though a positive fraction of its entries are arbitrarily corrupted. This extends
to the situation where a fraction of the entries are missing as well. In the second part of the talk, we present applications in computer vision. In video surveillance, for example, our methodology allows for the detection of
objects in a cluttered background. We show how the methodology can be adapted to simultaneously align a batch
of images and correct serious defects/corruptions in each image, opening new perspectives.
Philippe Rigollet

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.cs.princeton.edu/pipermail/ml-stat-talks/attachments/20121023/d88a11f5/attachment.htm>

More information about the Ml-stat-talks mailing list