On a Convex Logic Fragment for Learning and Reasoning

TL;DR

This paper introduces a convex fragment of {\

Contribution

It presents a new convex logic fragment that enables formulating learning problems with logical constraints as quadratic programming tasks.

Findings

The convex fragment guarantees handling of convex, linear-equivalent constraints.

Learning with kernel machines and collective classification can be formulated as quadratic programming.

The theoretical results are broadly applicable across various learning frameworks involving logical constraints.

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.