A Caltech Library Service

The Central Classifier Bound - A New Error Bound for the Classifier Chosen by Early Stopping

Bax, Eric and Çataltepe, Zehra and Sill, Joe (1997) The Central Classifier Bound - A New Error Bound for the Classifier Chosen by Early Stopping. California Institute of Technology , Pasadena, CA. (Unpublished)

Postscript - Submitted Version
See Usage Policy.

[img] PDF - Submitted Version
See Usage Policy.


Use this Persistent URL to link to this item:


Training with early stopping is the following process. Partition the in sample data into training and validation sets Begin with a random classifier g_(1-). Use an iterative method to decrease the error rate on the training data. Record the classifier at each iteration producing a series of snapshots g_1....g_M. Evaluate the error rate of each snapshot over the validation data. Deliver a minimum validation error classifier. g^* as the result of training.

Item Type:Report or Paper (Technical Report)
Additional Information:© 1997 California Institute of Technology. June 26, 1997. We thank Dr. Yaser Abu-Mostafa and Dr. Joel Franklin for their teaching and advice.
Group:Computer Science Technical Reports
Subject Keywords:machine learning learning theory, validation, early stopping, Vapnik Chervonenkis
Record Number:CaltechCSTR:1997.cs-tr-97-08
Persistent URL:
Usage Policy:You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format.
ID Code:26811
Deposited By: Imported from CaltechCSTR
Deposited On:25 Apr 2001
Last Modified:03 Oct 2019 03:18

Repository Staff Only: item control page