Improved Uniform Test Error Bounds

Bax, Eric (1997) Improved Uniform Test Error Bounds. California Institute of Technology , Pasadena, CA. (Unpublished) https://resolver.caltech.edu/CaltechCSTR:1997.cs-tr-97-15

Preview

Postscript - Submitted Version
See Usage Policy.
333kB

PDF - Submitted Version
See Usage Policy.
176kB

Use this Persistent URL to link to this item: https://resolver.caltech.edu/CaltechCSTR:1997.cs-tr-97-15

Abstract

We derive distribution-free uniform test error bounds that improve on VC-type bounds for validation. We show how to use knowledge of test inputs to improve the bounds. The bounds are sharp, but they require intense computation. We introduce a method to trade sharpness for speed of computation. Also, we compute the bounds for several test cases.

Item Type:	Report or Paper (Technical Report)
Additional Information:	© 1997 California Institute of Technology. I thank Dr Joel Franklin for his teaching advice and encouragement I thank Zehra Cataltepe, Sam Roweis, and Joe Sill for their many helpful conversations and pointers to literature in the development of this work. Also thanks to Dr. Yaser Abu-Mostafa for his informative and inspiring teaching.
Group:	Computer Science Technical Reports
Subject Keywords:	machine learning learning theory generalization Vapnik-Chervonenkis
DOI:	10.7907/Z9959FK4
Record Number:	CaltechCSTR:1997.cs-tr-97-15
Persistent URL:	https://resolver.caltech.edu/CaltechCSTR:1997.cs-tr-97-15
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:	26816
Collection:	CaltechCSTR
Deposited By:	Imported from CaltechCSTR
Deposited On:	25 Apr 2001
Last Modified:	03 Oct 2019 03:18

Repository Staff Only: item control page