ERROR BOUNDS FOR THE METHOD OF MINIMIZATION OF EMPIRICAL RISK.

Research output: Contribution to journalArticlepeer-review

Abstract

New nonasymptotic upper bounds are obtained for the probability of deviation of the minimum empirical risk from the minimum average risk in a class of problems that includes signal identification against an additive noise background under conditions of a priori uncertainty, as well as certain other pattern-recognition problems.

Original languageEnglish
Pages (from-to)33-42
Number of pages10
JournalProblems of Information Transmission
Volume17
Issue number1
Publication statusPublished - 1 Jan 1981

Fingerprint

Dive into the research topics of 'ERROR BOUNDS FOR THE METHOD OF MINIMIZATION OF EMPIRICAL RISK.'. Together they form a unique fingerprint.

Cite this