On a Convex Logic Fragment for Learning and Reasoning

Authors:
  • FGFrancesco Giannini
    Francesco Giannini
  • MDMichelangelo Diligenti
    Michelangelo Diligenti
  • MGMarco Gori
    Marco Gori
  • MMMarco Maggini
    Marco Maggini

Abstract
In this paper we introduce the convex fragment of {\L}ukasiewicz Logic and discuss its possible applications in different learning schemes. Indeed, the provided theoretical results are highly general, because they can be exploited in any learning framework involving logical constraints. The method is of particular interest since the fragment guarantees to deal with convex constraints, which are shown to be equivalent to a set of linear constraints. Within this framework, we are able to formulate learning with kernel machines as well as collective classification as a quadratic programming problem.