“High Dimension Statistical Problems: Practice and Theory”

SPEAKER: Narayana P Santhanam, Postdoctoral Researcher, UC BerkeleyABSTRACT: 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 inability of classical methods to handle problems in which the parameters associated with each data sample is comparable to the number of samples at hand.In particular, high dimension statistical problems are ubiquitous in biology, data analysis and business. In this talk we will introduce approaches for tackling some such problems.We begin with a demonstration of our approaches on text data in the context of classification problems. We will show very fast algorithms that stand up to (and in many cases, beat) sophisticated statistical learning techniques in performance and speed. We then develop the theory behind these approaches using ideas from information theory, number theory, combinatorics, analysis as well as tools in statistical learning.The big picture is to see this work as source coding driven by data analysis and biology, complementing the traditional communication/storage driven models. We conclude with a brief preview of some of the directions in which we are developing this work.BIO: Narayana Santhanam is a postdoctoral researcher hosted by Prof. Martin Wainwright in UC Berkeley. He obtained the B.Tech degree from IIT Madras, and MS and PhD with Prof. Alon Orlitsky from UC San Diego. He is interested in theory 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 award and the 2003 Capocelli Prize.HOST: Prof. Giuseppe Caire, caire@usc.edu

Location: Hughes Aircraft Electrical Engineering Center (EEB) - 248

Audiences: Everyone Is Invited

Contact: Mayumi Thrasher