Information, prediction, and query by committee

Research output: Chapter in Book/Report/Conference proceedingConference contribution

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 languageAmerican English
Title of host publicationAdvances in Neural Information Processing Systems 5, NIPS 1992
EditorsStephen Jose Hanson, Jack D. Cowan, C. Lee Giles
PublisherNeural information processing systems foundation
Pages483-490
Number of pages8
ISBN (Electronic)1558602747, 9781558602748
DOIs
StatePublished - 1992
Externally publishedYes
Event5th Advances in Neural Information Processing Systems, NIPS 1992 - Denver, United States
Duration: Nov 30 1992Dec 3 1992

Publication series

NameAdvances in Neural Information Processing Systems
Volume5

Conference

Conference5th Advances in Neural Information Processing Systems, NIPS 1992
Country/TerritoryUnited States
CityDenver
Period11/30/9212/3/92

ASJC Scopus subject areas

  • Signal Processing
  • Information Systems
  • Computer Networks and Communications

Fingerprint

Dive into the research topics of 'Information, prediction, and query by committee'. Together they form a unique fingerprint.

Cite this