Learning from a Population of Hypotheses

Michael Kearns, Hyunjune Sebastian Seung

Research output: Contribution to journalArticlepeer-review

14 Scopus citations


We introduce a new formal model in which a learning algorithm must combine a collection of potentially poor but statistically independent hypothesis functions in order to approximate an unknown target function arbitrarily well. Our motivation includes the question of how to make optimal use of multiple independent runs of a mediocre learning algorithm, as well as settings in which the many hypotheses are obtained by a distributed population of identical learning agents.

Original languageEnglish (US)
Pages (from-to)255-276
Number of pages22
JournalMachine Learning
Issue number2
StatePublished - Feb 1995

All Science Journal Classification (ASJC) codes

  • Software
  • Artificial Intelligence


  • PAC learning
  • computational learning theory
  • learning agents
  • machine learning


Dive into the research topics of 'Learning from a Population of Hypotheses'. Together they form a unique fingerprint.

Cite this