Results on learnability and the Vapnik-Chervonenkis dimension

Nathan Linial; Yishay Mansour; Ronald L. Rivest

doi:10.1109/sfcs.1988.21930

Results on learnability and the Vapnik-Chervonenkis dimension

Nathan Linial^*, Yishay Mansour, Ronald L. Rivest

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

12 Scopus citations

Abstract

The problem of learning a concept from examples in a distribution-free model is considered. The notion of dynamic sampling, wherein the number of examples examined can increase with the complexity of the target concept, is introduced. This method is used to establish the learnability of various concept classes with an infinite Vapnik-Chervonenkis (VC) dimension. An important variation on the problem of learning from examples, called approximating from examples, is also discussed. The problem of computing the VC dimension of a finite concept set defined on a finite domain is considered.

Original language	American English
Title of host publication	Annual Symposium on Foundations of Computer Science (Proceedings)
Publisher	Publ by IEEE
Pages	120-129
Number of pages	10
ISBN (Print)	0818608773, 9780818608773
DOIs	https://doi.org/10.1109/sfcs.1988.21930
State	Published - 1988
Externally published	Yes

Publication series

Name	Annual Symposium on Foundations of Computer Science (Proceedings)
ISSN (Print)	0272-5428

Bibliographical note

Funding Information:
* This paper was prepared with support from NSF Grant DCR-8607494, AR0 Grant DAAL-03-86-K-0171, and the Siemens Corporation.

Access to Document

10.1109/sfcs.1988.21930

Cite this

@inproceedings{e228dbd749b745ceabb543df1695b576,

title = "Results on learnability and the Vapnik-Chervonenkis dimension",

abstract = "The problem of learning a concept from examples in a distribution-free model is considered. The notion of dynamic sampling, wherein the number of examples examined can increase with the complexity of the target concept, is introduced. This method is used to establish the learnability of various concept classes with an infinite Vapnik-Chervonenkis (VC) dimension. An important variation on the problem of learning from examples, called approximating from examples, is also discussed. The problem of computing the VC dimension of a finite concept set defined on a finite domain is considered.",

author = "Nathan Linial and Yishay Mansour and Rivest, {Ronald L.}",

note = "Funding Information: * This paper was prepared with support from NSF Grant DCR-8607494, AR0 Grant DAAL-03-86-K-0171, and the Siemens Corporation.",

year = "1988",

doi = "10.1109/sfcs.1988.21930",

language = "American English",

isbn = "0818608773",

series = "Annual Symposium on Foundations of Computer Science (Proceedings)",

publisher = "Publ by IEEE",

pages = "120--129",

booktitle = "Annual Symposium on Foundations of Computer Science (Proceedings)",

}

Results on learnability and the Vapnik-Chervonenkis dimension. / Linial, Nathan; Mansour, Yishay; Rivest, Ronald L.
Annual Symposium on Foundations of Computer Science (Proceedings). Publ by IEEE, 1988. p. 120-129 (Annual Symposium on Foundations of Computer Science (Proceedings)).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Results on learnability and the Vapnik-Chervonenkis dimension

AU - Linial, Nathan

AU - Mansour, Yishay

AU - Rivest, Ronald L.

N1 - Funding Information: * This paper was prepared with support from NSF Grant DCR-8607494, AR0 Grant DAAL-03-86-K-0171, and the Siemens Corporation.

PY - 1988

Y1 - 1988

N2 - The problem of learning a concept from examples in a distribution-free model is considered. The notion of dynamic sampling, wherein the number of examples examined can increase with the complexity of the target concept, is introduced. This method is used to establish the learnability of various concept classes with an infinite Vapnik-Chervonenkis (VC) dimension. An important variation on the problem of learning from examples, called approximating from examples, is also discussed. The problem of computing the VC dimension of a finite concept set defined on a finite domain is considered.

AB - The problem of learning a concept from examples in a distribution-free model is considered. The notion of dynamic sampling, wherein the number of examples examined can increase with the complexity of the target concept, is introduced. This method is used to establish the learnability of various concept classes with an infinite Vapnik-Chervonenkis (VC) dimension. An important variation on the problem of learning from examples, called approximating from examples, is also discussed. The problem of computing the VC dimension of a finite concept set defined on a finite domain is considered.

UR - http://www.scopus.com/inward/record.url?scp=0024135612&partnerID=8YFLogxK

U2 - 10.1109/sfcs.1988.21930

DO - 10.1109/sfcs.1988.21930

M3 - Conference contribution

AN - SCOPUS:0024135612

SN - 0818608773

SN - 9780818608773

T3 - Annual Symposium on Foundations of Computer Science (Proceedings)

SP - 120

EP - 129

BT - Annual Symposium on Foundations of Computer Science (Proceedings)

PB - Publ by IEEE

ER -

Results on learnability and the Vapnik-Chervonenkis dimension

Abstract

Publication series

Bibliographical note

Access to Document

Other files and links

Fingerprint

Cite this