The one-inclusion graph algorithm is near-optimal for the prediction model of learning

The one-inclusion graph algorithm is near-optimal for the prediction model of learning

Haussler, Littlestone and Warmuth (1994) described a general-purpose algorithm for learning according to the prediction model, and proved an upper bound on the probability that their algorithm makes a mistake in terms of the number of examples seen and the Vapnik-Chervonenkis (VC) dimension of the c...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on information theory 2001-03, Vol.47 (3), p.1257-1261
Hauptverfasser: Yi Li, Long, P.M., Srinivasan, A.
Format: Artikel
Sprache:eng
Schlagworte:
Algorithms
Errors
Graphs
Information theory
Learning
Learning control systems
Mathematical models
Upper bounds
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Haussler, Littlestone and Warmuth (1994) described a general-purpose algorithm for learning according to the prediction model, and proved an upper bound on the probability that their algorithm makes a mistake in terms of the number of examples seen and the Vapnik-Chervonenkis (VC) dimension of the concept class being learned. We show that their bound is within a factor of 1+o(1) of the best possible such bound for any algorithm.
ISSN:0018-9448
1557-9654
DOI:10.1109/18.915700