Metric Entropy and Applications

Monday, February 20, 2012 - 1:30pm - 2:30pm
Lind 305
Wenbo Li (University of Delaware)
Metric entropy is defined as the logarithm of the minimum covering number of a compact set by balls of very small radius. In this series of lectures, we will provide an overview of various available techniques and significant applications to theory of approximation, machine learning, data compression, probability and statistics. All talks are accessible to graduate students in any areas of mathematics.