Game-theoretic probability: brief review
Vladimir Vovk (Royal Holloway, University of London)
January 9, 2014, 3:30PM
Abstract: The standard approach to probabilistic modelling is to assume a probability measure generating the observed outcomes. Game-theoretic probability weakens this assumption but still allows one to obtain many familiar results, such as laws of large numbers and iterated logarithm, central limit theorems, large deviation inequalities, and zero-one laws. It also leads to completely new results.
Background: The speaker (http://www.vovk.net/ ) is visiting asecolab to work on a joint project. He was one of the last students of great Andrei Kolmogorov, but since the mid 90s he focused on algorithmic learning and foundations of statistics. With Glenn Shafer (of Dempster-Shafer Theory) he wrote an influential book (http://tinyurl.com/kb8g924 ), reconstructing probability theory from gaming. Last term they ran a reading seminar at the Math Dept devoted to this book. Hence the talk.