Information, prediction, and query by committee

Yoav Freund; H. Sebastian Seung; Eli Shamir; Naftali Tishby

doi:10.5555/2987061.2987121

Information, prediction, and query by committee

Yoav Freund, H. Sebastian Seung, Eli Shamir, Naftali Tishby

Einstein Institute of Mathematics

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

38 Scopus citations

Abstract

We analyze the "query by committee" algorithm, a method for filtering informative queries from a random stream of inputs. We show that if the two-member committee algorithm achieves information gain with positive lower bound, then the prediction error decreases exponentially with the number of queries. We show that, in particular, this exponential decrease holds for query learning of thresholded smooth functions.

Original language	English
Title of host publication	Advances in Neural Information Processing Systems 5, NIPS 1992
Editors	Stephen Jose Hanson, Jack D. Cowan, C. Lee Giles
Publisher	Neural information processing systems foundation
Pages	483-490
Number of pages	8
ISBN (Electronic)	1558602747, 9781558602748
DOIs	https://doi.org/10.5555/2987061.2987121
State	Published - 1992
Event	5th Advances in Neural Information Processing Systems, NIPS 1992 - Denver, United States Duration: 30 Nov 1992 → 3 Dec 1992

Publication series

Name	Advances in Neural Information Processing Systems
Volume	5
ISSN (Print)	1049-5258

Conference

Conference	5th Advances in Neural Information Processing Systems, NIPS 1992
Country/Territory	United States
City	Denver
Period	30/11/92 → 3/12/92

Bibliographical note

Publisher Copyright:
© 1992 Neural information processing systems foundation. All rights reserved.

Access to Document

10.5555/2987061.2987121

Cite this

Freund, Y., Seung, H. S., Shamir, E., & Tishby, N. (1992). Information, prediction, and query by committee. In S. J. Hanson, J. D. Cowan, & C. L. Giles (Eds.), Advances in Neural Information Processing Systems 5, NIPS 1992 (pp. 483-490). (Advances in Neural Information Processing Systems; Vol. 5). Neural information processing systems foundation. https://doi.org/10.5555/2987061.2987121

@inproceedings{dabe9a11a9084f37be8a4bba4ef78b2b,

title = "Information, prediction, and query by committee",

abstract = "We analyze the {"}query by committee{"} algorithm, a method for filtering informative queries from a random stream of inputs. We show that if the two-member committee algorithm achieves information gain with positive lower bound, then the prediction error decreases exponentially with the number of queries. We show that, in particular, this exponential decrease holds for query learning of thresholded smooth functions.",

author = "Yoav Freund and Seung, \{H. Sebastian\} and Eli Shamir and Naftali Tishby",

note = "Publisher Copyright: {\textcopyright} 1992 Neural information processing systems foundation. All rights reserved.; 5th Advances in Neural Information Processing Systems, NIPS 1992 ; Conference date: 30-11-1992 Through 03-12-1992",

year = "1992",

doi = "10.5555/2987061.2987121",

language = "אנגלית",

series = "Advances in Neural Information Processing Systems",

publisher = "Neural information processing systems foundation",

pages = "483--490",

editor = "Hanson, \{Stephen Jose\} and Cowan, \{Jack D.\} and Giles, \{C. Lee\}",

booktitle = "Advances in Neural Information Processing Systems 5, NIPS 1992",

}

Freund, Y, Seung, HS, Shamir, E & Tishby, N 1992, Information, prediction, and query by committee. in SJ Hanson, JD Cowan & CL Giles (eds), Advances in Neural Information Processing Systems 5, NIPS 1992. Advances in Neural Information Processing Systems, vol. 5, Neural information processing systems foundation, pp. 483-490, 5th Advances in Neural Information Processing Systems, NIPS 1992, Denver, United States, 30/11/92. https://doi.org/10.5555/2987061.2987121

Information, prediction, and query by committee. / Freund, Yoav; Seung, H. Sebastian; Shamir, Eli et al.
Advances in Neural Information Processing Systems 5, NIPS 1992. ed. / Stephen Jose Hanson; Jack D. Cowan; C. Lee Giles. Neural information processing systems foundation, 1992. p. 483-490 (Advances in Neural Information Processing Systems; Vol. 5).

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

TY - GEN

T1 - Information, prediction, and query by committee

AU - Freund, Yoav

AU - Seung, H. Sebastian

AU - Shamir, Eli

AU - Tishby, Naftali

PY - 1992

Y1 - 1992

N2 - We analyze the "query by committee" algorithm, a method for filtering informative queries from a random stream of inputs. We show that if the two-member committee algorithm achieves information gain with positive lower bound, then the prediction error decreases exponentially with the number of queries. We show that, in particular, this exponential decrease holds for query learning of thresholded smooth functions.

AB - We analyze the "query by committee" algorithm, a method for filtering informative queries from a random stream of inputs. We show that if the two-member committee algorithm achieves information gain with positive lower bound, then the prediction error decreases exponentially with the number of queries. We show that, in particular, this exponential decrease holds for query learning of thresholded smooth functions.

UR - https://www.scopus.com/pages/publications/105021002031

U2 - 10.5555/2987061.2987121

DO - 10.5555/2987061.2987121

M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???

AN - SCOPUS:105021002031

T3 - Advances in Neural Information Processing Systems

SP - 483

EP - 490

BT - Advances in Neural Information Processing Systems 5, NIPS 1992

A2 - Hanson, Stephen Jose

A2 - Cowan, Jack D.

A2 - Giles, C. Lee

PB - Neural information processing systems foundation

T2 - 5th Advances in Neural Information Processing Systems, NIPS 1992

Y2 - 30 November 1992 through 3 December 1992

ER -

Information, prediction, and query by committee

Abstract

Publication series

Conference

Bibliographical note

Access to Document

Other files and links

Fingerprint

Cite this