Data Dependent Concentration Bounds for Sequential Prediction Algorithms

Abstract. We investigate the generalization behavior of sequential prediction (online) algorithms, when data are generated from a probability distribution. Using some newly developed probability inequalities, we are able to bound the total generalization performance of a learning algorithm in terms of its observed total loss. Consequences of this analysis will be illustrated with examples.

• Type: Conference
• Year: 2005
• Where: COLT
• Authors: Tong Zhang
• Keywords: COLT 2005, Generalization Behavior, Machine Learning, Observed Total Loss, Total Generalization Performance