Algorithmic Stability and Generalization Performance

Bousquet, O; Elisseeff, A

Local TagsRelease HistoryDetailsSummary

Algorithmic Stability and Generalization Performance

Bousquet, O., & Elisseeff, A. (2001). Algorithmic Stability and Generalization Performance. In T. Leen, T. Dietterich, & V. Tresp (Eds.), Advances in Neural Information Processing Systems 13 (pp. 196-202). Cambridge, MA, USA: MIT Press.

Item is Released

show all hide all

Basic

show hide

Item Permalink: https://hdl.handle.net/11858/00-001M-0000-0013-E2AA-C Version Permalink: https://hdl.handle.net/21.11116/0000-0005-0EFD-0

Genre: Conference Paper

Files

show Files

Locators

show

hide

Locator:
https://papers.nips.cc/paper/1854-algorithmic-stability-and-generalization-performance.pdf (Publisher version) Open Access status unknown

Description:
-

OA-Status:

Creators

show

hide

Creators:
Bousquet, O¹, Author
Elisseeff, A¹, Author

Affiliations:
1External Organizations, ou_persistent22

Content

show

hide

Free keywords: -

Abstract: We present a novel way of obtaining PAC-style bounds on the generalization error of learning algorithms, explicitly using their stability properties. A \em stable learner being one for which the learned solution does not change much for small changes in the training set. The bounds we obtain do not depend on any measure of the complexity of the hypothesis space (e.g. VC dimension) but rather depend on how the learning algorithm searches this space, and can thus be applied even when the VC dimension in infinite.
We demonstrate that regularization networks possess the required stability property and apply our method to obtain new bounds on their generalization performance.

Details

show

hide

Language(s):

Dates: Date issued: 2001-04

Publication Status: Issued

Pages: -

Publishing info: -

Table of Contents: -

Rev. Type: -

Identifiers: BibTex Citekey: 1437

Degree: -

Event

show

hide

Title: Fourteenth Annual Neural Information Processing Systems Conference (NIPS 2000)

Place of Event: Denver, CO, USA

Start-/End Date: 2000-11-27 - 2000-12-02

Legal Case

show

Project information

show

Source 1

show

hide

Title: Advances in Neural Information Processing Systems 13

Source Genre: Proceedings

Creator(s):
Leen, TK, Editor
Dietterich, TG, Editor
Tresp, V, Editor

Affiliations:
-

Publ. Info: Cambridge, MA, USA : MIT Press

Pages: - Volume / Issue: - Sequence Number: - Start / End Page: 196 - 202 Identifier: ISBN: 0-262-12241-3