Predicting nearly as well as the best pruning of a planar decision graph

Eiji Takimoto, Manfred K. Warmuth

Research output: Contribution to journalConference article

14 Citations (Scopus)

Abstract

We design efficient on-line algorithms that predict nearly as well as the best pruning of a planar decision graph. We assume that the graph has no cycles. As in the previous work on decision trees, we implicitly maintain one weight for each of the prunings (exponentially many). The method works for a large class of algorithms that update its weights multiplicatively. It can also be used to design algorithms that predict nearly as well as the best convex combination of prunings.

Original languageEnglish
Pages (from-to)217-235
Number of pages19
JournalTheoretical Computer Science
Volume288
Issue number2
DOIs
Publication statusPublished - Oct 16 2002
Externally publishedYes
EventAlgorithmic Learning Theory (ALT 1999) - Tokyo, Japan
Duration: Dec 6 1999Dec 8 1999

    Fingerprint

All Science Journal Classification (ASJC) codes

  • Theoretical Computer Science
  • Computer Science(all)

Cite this