Conservativeness and monotonicity for learning algorithms

Eiji Takimoto, Akira Maruoka

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

1 Citation (Scopus)

Abstract

In the framework of PAC-learning model, relationships between learning processes and information compressing processes are investigated. Information compressing processes are formulated as weak Occam algorithms. A weak Occam algorithm is a deterministic polynomial time algorithm that, when given m examples of unknown function, outputs, with high probability, a representation of a function that is consistent with the examples and belongs to a function class with complexity o(m). It has been shown that a weak Occam algorithm is also a consistent PAC-learning algorithm. In this extended abstract, it is shown that the converse does not hold by giving a PAC-learning algorithm that is not a weak Occam algorithm, and also some natural properties, called conservativeness and monotonicity, for learning algorithms that might help the converse hold are given. In particular, the conditions that make a conservative PAC-learning algorithm a weak Occam algorithm are given, and it is shown that, under some natural conditions, a monotone PAC-learning algorithm for a hypothesis class can be transformed to a weak Occam algorithm without changing the hypothesis class.

Original languageEnglish
Title of host publicationProc 6 Annu ACM Conf Comput Learn Theory
PublisherPubl by ACM
Pages377-383
Number of pages7
ISBN (Print)0897916115, 9780897916110
DOIs
Publication statusPublished - 1993
Externally publishedYes
EventProceedings of the 6th Annual ACM Conference on Computational Learning Theory - Santa Cruz, CA, USA
Duration: Jul 26 1993Jul 28 1993

Publication series

NameProc 6 Annu ACM Conf Comput Learn Theory

Other

OtherProceedings of the 6th Annual ACM Conference on Computational Learning Theory
CitySanta Cruz, CA, USA
Period7/26/937/28/93

All Science Journal Classification (ASJC) codes

  • Engineering(all)

Fingerprint Dive into the research topics of 'Conservativeness and monotonicity for learning algorithms'. Together they form a unique fingerprint.

  • Cite this

    Takimoto, E., & Maruoka, A. (1993). Conservativeness and monotonicity for learning algorithms. In Proc 6 Annu ACM Conf Comput Learn Theory (pp. 377-383). (Proc 6 Annu ACM Conf Comput Learn Theory). Publ by ACM. https://doi.org/10.1145/168304.168381