Research Note on Decision Lists

  • Authors:

  • Ron Kohavi;Scott Benson

  • Affiliations:

  • Computer Science Dept., Stanford University, Stanford, CA 94305. RONNYK@CS.STANFORD.EDU;Computer Science Dept., Stanford University, Stanford, CA 94305. SBENSON@CS.STANFORD.EDU

  • Venue:
  • Machine Learning
  • Year:
  • 1993

Quantified Score

Hi-index 0.00

Visualization

Abstract

In his article “Learning Decision Lists,” Rivest proves that (k-DNF ∪ k-CNF) is a proper subset of k-DL. The proof is based on the following incorrect claim:… if a function f has a prime implicant of size t, then f has no k-DNF representation if k t.In this note, we show a counterexample to the claim and then prove a stronger theorem, from which Rivest's theorem follows as a corollary.