Linear and piecewise linear data analysis
Speaker: Arthur Szlam , Courant Institute of Mathematical Sciences, NYU
Date: February 10 2011
Time: 4:30PM to 5:30PM
Location: Patil/ Kiva Sem Rm 32-G449
Host: Lorenzo Rosasco, Istituto Italiano di Tecnologia; CBCL, MIT
Contact: Kathleen Sullivan, (617) 253-0551, kdsulliv@mit.edu
Relevant URL: http://cbcl.mit.edu/The seminar is co-hosted by the
Brain and Machine Seminar Series &
Image and Computing Seminar Series.
Abstract: Many data sets arising from signal processing or machine learning problems can be approximately modeled as a union of $K$ low dimensional linear sets. In this talk I will start by discussing the case $K=1$, which remains a surprisingly active area of research, despite more than a hundred years of history and a good understanding of the mathematics of the problem for many notions of ``approximately'' and ``low''. For larger values of $K$, although heuristic methods have proved successful in applications, many basic mathematical and computational questions remain open. I will talk about some regimes where we have made progress, and then give some fun examples in less easy regimes where the math remains murky.
The Brain Machine 2011 Seminar Series is being organized by the IIT@MIT lab (a joint lab between MIT and the Italian Institute of Technology.)
See other events that are part of Brains and Machines Seminar Series 2010/2011
See other events happening in February 2011
