Localized rademacher complexities

Peter L. Bartlett; Olivier Bousquet; Shahar Mendelson

doi:10.1007/3-540-45435-7_4

Localized rademacher complexities

Peter L. Bartlett, Olivier Bousquet, Shahar Mendelson

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

50 Citations (Scopus)

Abstract

We investigate the behaviour of global and local Rademacher averages. We present new error bounds which are based on the local averages and indicate how data-dependent local averages can be estimated without a priori knowledge of the class at hand.

Original language	English
Title of host publication	Computational Learning Theory - 15th Annual Conference on Computational Learning Theory, COLT 2002, Proceedings
Editors	Jyrki Kivinen, Robert H. Sloan
Publisher	Springer Verlag
Pages	44-58
Number of pages	15
ISBN (Electronic)	354043836X, 9783540438366
DOIs	https://doi.org/10.1007/3-540-45435-7_4
Publication status	Published - 2002
Event	15th Annual Conference on Computational Learning Theory, COLT 2002 - Sydney, Australia Duration: 8 Jul 2002 → 10 Jul 2002

Publication series

Name	Lecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science)
Volume	2375
ISSN (Print)	0302-9743

Conference

Conference	15th Annual Conference on Computational Learning Theory, COLT 2002
Country/Territory	Australia
City	Sydney
Period	8/07/02 → 10/07/02

Access to Document

10.1007/3-540-45435-7_4

Cite this

Bartlett, P. L., Bousquet, O., & Mendelson, S. (2002). Localized rademacher complexities. In J. Kivinen, & R. H. Sloan (Eds.), Computational Learning Theory - 15th Annual Conference on Computational Learning Theory, COLT 2002, Proceedings (pp. 44-58). (Lecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science); Vol. 2375). Springer Verlag. https://doi.org/10.1007/3-540-45435-7_4

Bartlett, Peter L. ; Bousquet, Olivier ; Mendelson, Shahar. / Localized rademacher complexities. Computational Learning Theory - 15th Annual Conference on Computational Learning Theory, COLT 2002, Proceedings. editor / Jyrki Kivinen ; Robert H. Sloan. Springer Verlag, 2002. pp. 44-58 (Lecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science)).

@inproceedings{548fd5d27d8445f382ab3fc8dcbdf3a4,

title = "Localized rademacher complexities",

abstract = "We investigate the behaviour of global and local Rademacher averages. We present new error bounds which are based on the local averages and indicate how data-dependent local averages can be estimated without a priori knowledge of the class at hand.",

author = "Bartlett, {Peter L.} and Olivier Bousquet and Shahar Mendelson",

note = "Publisher Copyright: {\textcopyright} Springer-Verlag Berlin Heidelberg 2002.; 15th Annual Conference on Computational Learning Theory, COLT 2002 ; Conference date: 08-07-2002 Through 10-07-2002",

year = "2002",

doi = "10.1007/3-540-45435-7_4",

language = "English",

series = "Lecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science)",

publisher = "Springer Verlag",

pages = "44--58",

editor = "Jyrki Kivinen and Sloan, {Robert H.}",

booktitle = "Computational Learning Theory - 15th Annual Conference on Computational Learning Theory, COLT 2002, Proceedings",

address = "Germany",

}

Bartlett, PL, Bousquet, O & Mendelson, S 2002, Localized rademacher complexities. in J Kivinen & RH Sloan (eds), Computational Learning Theory - 15th Annual Conference on Computational Learning Theory, COLT 2002, Proceedings. Lecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science), vol. 2375, Springer Verlag, pp. 44-58, 15th Annual Conference on Computational Learning Theory, COLT 2002, Sydney, Australia, 8/07/02. https://doi.org/10.1007/3-540-45435-7_4

Localized rademacher complexities. / Bartlett, Peter L.; Bousquet, Olivier; Mendelson, Shahar.
Computational Learning Theory - 15th Annual Conference on Computational Learning Theory, COLT 2002, Proceedings. ed. / Jyrki Kivinen; Robert H. Sloan. Springer Verlag, 2002. p. 44-58 (Lecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science); Vol. 2375).

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

TY - GEN

T1 - Localized rademacher complexities

AU - Bartlett, Peter L.

AU - Bousquet, Olivier

AU - Mendelson, Shahar

PY - 2002

Y1 - 2002

N2 - We investigate the behaviour of global and local Rademacher averages. We present new error bounds which are based on the local averages and indicate how data-dependent local averages can be estimated without a priori knowledge of the class at hand.

AB - We investigate the behaviour of global and local Rademacher averages. We present new error bounds which are based on the local averages and indicate how data-dependent local averages can be estimated without a priori knowledge of the class at hand.

UR - http://www.scopus.com/inward/record.url?scp=84937440359&partnerID=8YFLogxK

U2 - 10.1007/3-540-45435-7_4

DO - 10.1007/3-540-45435-7_4

M3 - Conference contribution

T3 - Lecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science)

SP - 44

EP - 58

BT - Computational Learning Theory - 15th Annual Conference on Computational Learning Theory, COLT 2002, Proceedings

A2 - Kivinen, Jyrki

A2 - Sloan, Robert H.

PB - Springer Verlag

T2 - 15th Annual Conference on Computational Learning Theory, COLT 2002

Y2 - 8 July 2002 through 10 July 2002

ER -

Bartlett PL, Bousquet O, Mendelson S. Localized rademacher complexities. In Kivinen J, Sloan RH, editors, Computational Learning Theory - 15th Annual Conference on Computational Learning Theory, COLT 2002, Proceedings. Springer Verlag. 2002. p. 44-58. (Lecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science)). doi: 10.1007/3-540-45435-7_4

Localized rademacher complexities

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this