|
 TITLE:
High-Dimensional Statistical Problems: Practice and Theory
SPEAKER: Narayana P. Santhanam (UC Berkeley)
DATE: 2:00 - 3:00 PM, Tuesday, November 18, 2008
LOCATION: Eureka, 1U
ABSTRACT:
For advances in biology, computation and storage, we have invited the "curse
of dimensionality" upon many problems that concern the modern engineer. The
colorful phrase in quotes coined by Bellman refers to the usual inability of
classical methods to handle problem instances wherein the number of parameters
associated with each data sample is comparable to the number of data samples
we have to work on.
In this talk, we first focus on the problem of discrete distribution
estimation in the undersampled regime, and develop a theory to tackle this
problem using ideas from information theory, number theory, combinatorics,
analysis, as well as tools in statistical learning. When classifying text,
these approaches yield very fast algorithms that stand up to (and in many
cases, beat) support vector machines in both performance and speed.
We then consider modeling more complex Markov random fields, this time,
drawing connections with statistical physics as well. We conclude with a brief
preview of some of the directions in which we are developing this work.
The big picture is to see this work as source coding driven by data analysis,
complementing the traditional communication/storage driven models.
BIOGRAPHY:
Narayana Prasad Santhanam will be an assistant professor at the University of
Hawaii, Manoa, from January 2009. In 2007 and 2008, he was a postdoctoral
researcher hosted by Prof. Martin Wainwright at UC Berkeley. He obtained his
B.Tech degree from IIT Madras, and MS and PhD degrees with Prof. Alon Orlitsky
from UC San Diego.
He is interested in theories and applications related to high-dimensional
problems, statistical learning, information theory, and
combinatorial/probabilistic problems in general. He is the recipient of the
2006 Information Theory Society Best Paper Award and the 2003 Capocelli Prize.
|
|
|
printable version
