Drifting Games

We consider the problem of learning to predict as well as the best in a group of experts making continuous predictions. We assume the learning algorithm has prior knowledge of the maximum number of mistakes of the best expert. We propose a new master strategy that achieves the best known performance for online learning with continuous experts in the mistake bounded model. Our ideas are based on drifting games, a generalization of boosting and online learning algorithms. We also prove new lower bounds based on the drifting games framework which, though not as tight as previous bounds, have simpler proofs and do not require an enormous number of experts.

• Type: Conference
• Year: 1999
• Where: COLT
• Authors: Robert E. Schapire
• Keywords: COLT 1999, Learning Algorithms, Machine Learning, Mistake Bounded Model, Online Learning