On the Estimation of Asymptotic Error Probability

Research output: Article

Abstract

In many actual learning problems, a sequence of decision functions is generated, and one has to estimate the limit of the error probabilities associated with these decision functions. This correspondence proposes a simple algorithm for the finite hypothesis testing problem. The procedure works in parallel with the iterative estimation of the decision function and utilizes in this way the same labeled samples for training and testing. A mild condition on the behavior of the probability of error of the sequence of decision rules is shown to imply strong convergence of a sequence of estimates of the probability of error.

Original languageEnglish
Pages (from-to)277-278
Number of pages2
JournalIEEE Transactions on Information Theory
Volume20
Issue number2
DOIs
Publication statusPublished - 1974

Fingerprint

Testing
hypothesis testing
Error probability
learning

ASJC Scopus subject areas

  • Computer Science Applications
  • Information Systems
  • Library and Information Sciences
  • Electrical and Electronic Engineering

Cite this

On the Estimation of Asymptotic Error Probability. / Györfi, L.

In: IEEE Transactions on Information Theory, Vol. 20, No. 2, 1974, p. 277-278.

Research output: Article

@article{fd99786e64994d04b2d8149d4a48a7b5,
title = "On the Estimation of Asymptotic Error Probability",
abstract = "In many actual learning problems, a sequence of decision functions is generated, and one has to estimate the limit of the error probabilities associated with these decision functions. This correspondence proposes a simple algorithm for the finite hypothesis testing problem. The procedure works in parallel with the iterative estimation of the decision function and utilizes in this way the same labeled samples for training and testing. A mild condition on the behavior of the probability of error of the sequence of decision rules is shown to imply strong convergence of a sequence of estimates of the probability of error.",
author = "L. Gy{\"o}rfi",
year = "1974",
doi = "10.1109/TIT.1974.1055182",
language = "English",
volume = "20",
pages = "277--278",
journal = "IEEE Transactions on Information Theory",
issn = "0018-9448",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "2",

}

TY - JOUR

T1 - On the Estimation of Asymptotic Error Probability

AU - Györfi, L.

PY - 1974

Y1 - 1974

N2 - In many actual learning problems, a sequence of decision functions is generated, and one has to estimate the limit of the error probabilities associated with these decision functions. This correspondence proposes a simple algorithm for the finite hypothesis testing problem. The procedure works in parallel with the iterative estimation of the decision function and utilizes in this way the same labeled samples for training and testing. A mild condition on the behavior of the probability of error of the sequence of decision rules is shown to imply strong convergence of a sequence of estimates of the probability of error.

AB - In many actual learning problems, a sequence of decision functions is generated, and one has to estimate the limit of the error probabilities associated with these decision functions. This correspondence proposes a simple algorithm for the finite hypothesis testing problem. The procedure works in parallel with the iterative estimation of the decision function and utilizes in this way the same labeled samples for training and testing. A mild condition on the behavior of the probability of error of the sequence of decision rules is shown to imply strong convergence of a sequence of estimates of the probability of error.

UR - http://www.scopus.com/inward/record.url?scp=0016034984&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0016034984&partnerID=8YFLogxK

U2 - 10.1109/TIT.1974.1055182

DO - 10.1109/TIT.1974.1055182

M3 - Article

AN - SCOPUS:0016034984

VL - 20

SP - 277

EP - 278

JO - IEEE Transactions on Information Theory

JF - IEEE Transactions on Information Theory

SN - 0018-9448

IS - 2

ER -