A Unified Study on Sequentiality in Universal Classification With Empirically Observed Statistics

In the binary hypothesis testing problem, it is well known that sequentiality in taking samples eradicates the trade-off between two error exponents, yet implementing the optimal test requires the knowledge of the underlying distributions, say <inline-formula> <tex-math notation="LaTeX...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE transactions on information theory Jg. 71; H. 3; S. 1546 - 1569
Hauptverfasser:	Li, Ching-Fang, Wang, I-Hsiang
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	IEEE 01.03.2025
Schlagworte:	Bayes methods Electrical engineering error exponents Error probability Hands Indexes Lower bound Reliability Seminars sequential composite hypothesis testing Testing Training Universal classification
ISSN:	0018-9448, 1557-9654
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!