### 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 language | English |
---|---|

Pages (from-to) | 277-278 |

Number of pages | 2 |

Journal | IEEE Transactions on Information Theory |

Volume | 20 |

Issue number | 2 |

DOIs | |

Publication status | Published - 1974 |

### Fingerprint

### 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.

Research output: Contribution to journal › Article

*IEEE Transactions on Information Theory*, vol. 20, no. 2, pp. 277-278. https://doi.org/10.1109/TIT.1974.1055182

}

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 -