CaltechAUTHORS
  A Caltech Library Service

No Free Lunch for Early Stopping

Çataltepe, Zehra and Abu-Mostafa, Yaser S. and Magdon-Ismail, Malik (1999) No Free Lunch for Early Stopping. Neural Computation, 11 (4). pp. 995-1009. ISSN 0899-7667. doi:10.1162/089976699300016557. https://resolver.caltech.edu/CaltechAUTHORS:20111201-140641206

[img]
Preview
PDF - Published Version
See Usage Policy.

177kB

Use this Persistent URL to link to this item: https://resolver.caltech.edu/CaltechAUTHORS:20111201-140641206

Abstract

We show that with a uniform prior on models having the same training error, early stopping at some fixed training error above the training error minimum results in an increase in the expected generalization error.


Item Type:Article
Related URLs:
URLURL TypeDescription
http://dx.doi.org/10.1162/089976699300016557DOIUNSPECIFIED
http://www.mitpressjournals.org/doi/abs/10.1162/089976699300016557PublisherUNSPECIFIED
Additional Information:© 1999 Massachusetts Institute of Technology. Received January 20, 1998; accepted August 6, 1998. Posted Online March 13, 2006. We thank members of the Caltech Learning Systems Group; Amir Atiya, Alexander Nicholson, Joseph Sill, and Xubo Song, for many useful discussions, and two anonymous referees for their comments that improved the presentation of this article.
Issue or Number:4
DOI:10.1162/089976699300016557
Record Number:CaltechAUTHORS:20111201-140641206
Persistent URL:https://resolver.caltech.edu/CaltechAUTHORS:20111201-140641206
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:28277
Collection:CaltechAUTHORS
Deposited By: Tony Diaz
Deposited On:19 Jan 2012 21:47
Last Modified:09 Nov 2021 16:55

Repository Staff Only: item control page