How to Learn Probability Without Learning

Tuesday, November 3, 2015 - 4:00pm

Event Calendar Category

LIDS Seminar Series

Speaker Name

Young-Han Kim


Univ. of California, San Diego

Building and Room Number



As Laplace famously asked ``What is the probability that the sun will rise tomorrow?,'' inferring the probability underlying a given data sample is at the core of statistics. In this talk, I will present a general principle of assigning probabilities to sequential data based on a somewhat arcane theory of universal probability, which has been developed (sometimes in disguise) in ergodic theory (Ornstein, Bailey, Morvai, Weiss), data compression (Ziv, Lempel, Rissanen, Willems, Shtarkov, Tjalkens), and sequential prediction (Cover, Feder, Merhav, Gutman, Gyorfi, Lugosi). I will explore the main features and applications of universal probability assignment through a few examples ranging from classification of nucleotide sequences to causality inference on time series data.

Based on joint work with Jiantao Jiao (Stanford), Sunyoung Kwon (SNU, Korea), Haim Permuter (Ben Gurion), Tsachy Weissman (Stanford), and Sungroh Yoon (SNU, Korea).


Young-Han Kim received his B.S. degree in Electrical Engineering from Seoul National University in 1996 and his Ph.D. degree in Electrical Engineering (M.S. degrees in Statistics and in Electrical Engineering) from Stanford University in 2006. Since then he has been a faculty member in the Department of Electrical and Computer Engineering at the University of California, San Diego, where he is currently an Associate Professor.

Professor Kim is a recipient of the NSF CAREER Award (2008), the US-Israel BSF Bergmann Memorial Award (2009), the IEEE Information Theory Paper Award (2012), and the first IEEE James L. Massey Research and Teaching Award (2015). He is an IEEE Fellow. His research interests include information theory, communication engineering, and data science. He has coauthored the book Network Information Theory, which has been used widely as a textbook on the topic.

Reception information

Reception to follow.