Less is More: Robustness and Sparsity in Statistics
Laurent El Ghaoui
Department of Electrical Engineering and Computer Science
University of California, Berkeley
Wednesday, May 16, 2007
4:30 - 5:30 PM
Terman Engineering Center, Room 453
Abstract:
The past decade has witnessed a tremendous progress in the
understanding of convex optimization, in terms of models, complexity,
and algorithms. This growth has fueled major progress in robust
optimization, which addresses decision problems with partially known
data. We review some of these advances and outline applications in
statistics, with an emphasis on the need for sparse solutions and
robustness in classification, regression, covariance estimation and
principal component analysis.
Bio:
I graduated from Ecole Polytechnique (Palaiseau, France) in 1985, and
obtained my PhD in Aeronautics and Astronautics at Stanford University
in March 1990. I was a faculty member of the Ecole Nationale
Superieure de Techniques Avancees (Paris, France) from 1992 until
1999, and held part-time teaching appointments at Ecole Polytechnique
within the Applied Mathematics department and Universite de Paris-I
(La Sorbonne) in the Mathematics in Economy program. In 1998, I was
awarded the Bronze Medal for Engineering Sciences, from the Centre
National de la Recherche Scientifique, France. I joined the Berkeley
faculty in April 1999 as an Acting Associate Professor, and obtained
my tenure in May 2001. I have been on leave from UC since July 2003 to
work for SAC Capital Management, a hedge fund based in New York and
Connecticut.
Operations Research Colloquia: http://or.stanford.edu/oras_seminars.html