A decision-theoretic generalization of on-line learning and an application to boosting


In the rst part of the paper we consider the problem of dynamically apportioning resources among a set of options in a worst-case on-line framework. The model we study can be interpreted as a broad, abstract extension of the well-studied on-line prediction model to a general decision-theoretic setting. We show that the multiplicative weight-update rule of Littlestone and Warmuth 15] can be adapted to this model yielding bounds that are slightly weaker in some cases, but applicable to a considerably more general class of learning problems. We show how the resulting learning algorithm can be applied to a variety of problems, including gambling, multiple-outcome prediction, repeated games and prediction of points in R n. In the second part of the paper we apply the multiplicative weight-update technique to derive a new boosting algorithm. This boosting algorithm does not require any prior knowledge about the performance of the weak learning algorithm. We also study generalizations of the new boosting algorithm to the problem of learning functions whose range, rather than being binary, is an arbitrary nite set or a bounded segment of the real line.

DOI: 10.1007/3-540-59119-2_166

Extracted Key Phrases

Showing 1-10 of 5,447 extracted citations
Citations per Year

12,852 Citations

Semantic Scholar estimates that this publication has received between 12,174 and 13,564 citations based on the available data.

See our FAQ for additional information.