Kernel Machines and Boolean Functions

We give results about the learnability and required complexity of logical formulae to solve classification problems. These results are obtained by linking propositional logic with kernel machines. In particular we show that decision trees and disjunctive normal forms (DNF) can be represented by the help of a special kernel, linking regularized risk to separation margin. Subsequently we derive a number of lower bounds on the required complexity of logic formulae using properties of algorithms for generation of linear estimators, such as perceptron and maximal perceptron learning.

• Type: Conference
• Year: 2001
• Where: NIPS
• Authors: Adam Kowalczyk, Alex J. Smola, Robert C. Williamson
• Keywords: Disjunctive Normal Forms, Logical Formulae, NIPS 2001, NIPS 2007, Required Complexity