The role of machine learning in the nonparametric prediction of time

László Györfi (Budapest University)
Wednesday, February 15, 2017 - 10:00am
WIAS, Erhard-Schmidt-Saal, Mohrenstraße 39, 10117 Berlin

The main purpose of this paper is to consider the prediction of stationary time series for various losses: squared loss (regression problem), $0, 1$ loss (pattern recognition) and log utility (growth optimal portfolio selection). We are interested in universal prediction rules, which are consistent for all possible stationary and ergodic processes. Such rules can be constructed using aggregation techniques of machine learning by combining elementary rules (experts) in data dependent way.