On the parameterised complexity of learning patterns

Frank Stephan, Ryo Yoshinaka, Thomas Zeugmann

Research output: Contribution to conferencePaper

8 Citations (Scopus)

Abstract

Angluin (1980) showed that there is a consistent and conservative learner for the class of non-erasing pattern languages; however, most of these learners are NP-hard. In the current work, the complexity of consistent polynomial time learners for the class of non-erasing pattern languages is revisited, with the goal to close one gap left by Angluin, namely the question on what happens if the learner is not required to output each time a consistent pattern of maximum possible length. It is shown that consistent learners are non-uniformly W[1]-hard inside the fixed-parameter hierarchy of Downey and Fellows (1999), and that there is also a W[1]-complete such learner. Only when one requires that the learner is in addition both, conservative and class-preserving, then one can show that the learning task is NP-hard for certain alphabet-sizes.

Original languageEnglish
Pages277-281
Number of pages5
DOIs
Publication statusPublished - 2012 Dec 1
Externally publishedYes
Event26th Annual International Symposium on Computer and Information Science, ISCIS 2011 - London, United Kingdom
Duration: 2011 Sep 262011 Sep 28

Other

Other26th Annual International Symposium on Computer and Information Science, ISCIS 2011
CountryUnited Kingdom
CityLondon
Period11/9/2611/9/28

ASJC Scopus subject areas

  • Computer Science (miscellaneous)
  • Information Systems

Fingerprint Dive into the research topics of 'On the parameterised complexity of learning patterns'. Together they form a unique fingerprint.

  • Cite this

    Stephan, F., Yoshinaka, R., & Zeugmann, T. (2012). On the parameterised complexity of learning patterns. 277-281. Paper presented at 26th Annual International Symposium on Computer and Information Science, ISCIS 2011, London, United Kingdom. https://doi.org/10.1007/978-1-4471-2155-8-35