A Decision Theoretic Generalization of On-Line Learning and an Application to Boosting
作者： R. Schapire , Y. Freund
DOI:
关键词: Repeated game 、 Theoretical computer science 、 Bounded function 、 Multiplicative function 、 Range (mathematics) 、 Finite set 、 Computer science 、 Set (abstract data type) 、 Generalization 、 Boosting (machine learning)
摘要: In the first 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 Littlestone–Warmuth rule 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 …
参考文章(0)