Computer Science
Hi everyone,
The following talk will take place at the Computer Science department
this Tuesday (April 9th) at 14:30.
Speaker: Aryeh Kontorovich
Title: Adaptive Metric Dimensionality Reduction
We initiate the study of dimensionality reduction in general metric
 spaces in the context of supervised learning. Our statistical
 contribution consists of tight Rademacher bounds for Lipschitz
 functions in metric spaces that are doubling, or nearly doubling.
 As a by-product, we obtain a new theoretical explanation for the
 empirically reported improvements gained by pre-processing Euclidean
 data by PCA (Principal Components Analysis) prior to constructing a
 linear classifier. On the algorithmic front, we describe an analogue
 of PCA for metric spaces, namely an efficient procedure that
 approximates the data's intrinsic dimension, which is often much
 lower than the ambient dimension. Thus, our approach can exploit the dual
 benefits of low dimensionality: (1) more efficient proximity search
 algorithms, and (2) more optimistic generalization bounds.
Short bio:
Aryeh Kontorovich received his undergraduate degree in
mathematics with a certificate in applied mathematics from
Princeton University in 2001. His M.Sc. and Ph.D. are from
Carnegie Mellon University, where he graduated in 2007. After
a postdoctoral fellowship at the Weizmann Institute of
Science, he joined the Computer Science department at
Ben-Gurion University of the Negev in 2009 as an assistant
professor; this is his current position. His research
interests are mainly in machine learning, with a focus on
probability, statistics, automata theory and metric spaces.
Technion Math. Net (TECHMATH)
Editor: Michael Cwikel   <> 
Announcement from: Orly Avner   <>