A Loss Bound Model for On-Line Stochastic Prediction Algorithms

In this paper, we consider the problem of on-line prediction in which at each time an unlabeled instance is given and then a prediction algorithm outputs a probability distribution over the set of labels rather than {0, 1}-values before it sees the correct label. For this setting, we propose a weigh...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Information and computation Jg. 119; H. 1; S. 39 - 54
1. Verfasser:	Yamanishi, K.
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	San Diego, CA Elsevier Inc 15.05.1995 Elsevier
Schlagworte:	Algorithmics. Computability. Computer arithmetics Applied sciences Computer science; control theory; systems Exact sciences and technology Theoretical computing Bayes estimation Lower bound Stochastic model Upper bound Parameter estimation Probability law Coding Prediction Algorithm Sequential estimation
ISSN:	0890-5401, 1090-2651
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!