Values and Patterns

Topic:Values and Patterns
Speaker:Alon Orlitsky
Affiliation:Depts. of ECE and CSE, University of California at San Diego
Date:Monday, April 27
Time/Room:11:15am - 12:15pm/S-101

Via four applications: distribution modeling, probability estimation, data compression, and classification, we argue that when learning from data, discrete values should be ignored except for just their appearance-order pattern. Along the way, we encounter Laplace, Good, Turing, Hardy, Ramanujan, Fisher, Shakespeare, and Shannon. The material will be presented in two independent parts. Based on work with P. Santhanam, K. Viswanathan, J. Zhang, and others.