On universal learning algorithms

Oded Goldreich, Dana Ron

Research output: Contribution to journalArticlepeer-review

Abstract

We observe that there exists a universal learning algorithm that PAC-learns every concept class within complexity that is linearly related to the complexity of the best learning algorithm for this class. This observation is derived by an adaptation, to the learning context, of Levin's proof of the existence of optimal algorithms for NP.

Original languageEnglish
Pages (from-to)131-136
Number of pages6
JournalInformation Processing Letters
Volume63
Issue number3
DOIs
StatePublished - 14 Aug 1997
Externally publishedYes

Keywords

  • PAC-learning
  • Theorey of computation

Fingerprint

Dive into the research topics of 'On universal learning algorithms'. Together they form a unique fingerprint.

Cite this