Regularizers for Structured Sparsity

Speaker:        Prof. Massimiliano Pontil
                University College London

Title:          "Regularizers for Structured Sparsity"

Date:           Tuesday, 18 March 2014

Time:           11:00am - 12 noon

Venue:          Room 2463 (near lifts 25/26), HKUST

Abstract:

We study the problem of learning a sparse linear regression vector under
additional conditions on its sparsity pattern. This problem is relevant in
machine learning, signal processing and statistics. We present a
regularization framework for structured sparsity in which the regularizers
are formulated as an infimum over a family of quadratics. We establish
some basic properties of these regularizers, discuss some examples where
they can be computed explicitly and present a convergent optimization
algorithm for solving the associated regularized least squares problem.
Finally, we discuss extensions of the framework to spectral regularization
and report on numerical experiments on different matrix completion and
multitask learning problems.


******************
Biogrpahy:

Massimiliano Pontil received an MSc degree in Physics from the University
of Genova in 1994 (summa cum laude) and a PhD in Physics from the same
University in 1999. He spent approximately half of the PhD studies at the
Massachusetts Institute of Technology (MIT) as a Visiting Researcher.
Massimiliano is Professor and EPSRC Advanced Research Fellow in the
Department of Computer Science at University College London (UCL). At UCL
he has also been a Lecturer, between January 2003 and September 2006, and
a Reader between October 2006 and September 2010. Before joining UCL,
Massimiliano was a Research Associate in the Department of Information
Engineering at University of Siena (2001--2002) and a Post-doctoral Fellow
in the Center for Biological and Computational Learning at the
Massachusetts Institute of Technology (MIT) (1998--2000). He has also been
a Visiting Fellow at the Isaac Newton Institute for Mathematical Sciences
in Cambridge, at the Catholic University of Leuven, at the University of
Chicago and at the City University of Hong Kong, among others. His
research interests are in the area of machine learning and pattern
recognition, with a focus on regularization methods, convex optimization
and statistical estimation. He also studied machine learning applications
arising in Computational Vision, Natural Language Processing and
Bioinformatics. He has published about hundred papers in the above
research areas, has been on the programme committee of the main machine
learning conferences, including COLT (2005, 2006, 2008, 2009, 2010) and
ICML (2004, 2009) and is an Associate Editor of the Machine Learning
Journal, Statistics and Computing and Action Editor for the Journal of
Machine Learning Research.