Learning programs with magic values

TL;DR

This paper presents an inductive logic programming method that efficiently learns programs with magic values, outperforming existing methods and handling infinite and large domains.

Contribution

Introduces a novel ILP approach for learning magic values in programs, capable of handling infinite and large domains with improved accuracy and efficiency.

Findings

Outperforms existing approaches in accuracy and speed

Learns magic values from infinite domains like pi

Scales to domains with millions of constants

Abstract

A magic value in a program is a constant symbol that is essential for the execution of the program but has no clear explanation for its choice. Learning programs with magic values is difficult for existing program synthesis approaches. To overcome this limitation, we introduce an inductive logic programming approach to efficiently learn programs with magic values. Our experiments on diverse domains, including program synthesis, drug design, and game playing, show that our approach can (i) outperform existing approaches in terms of predictive accuracies and learning times, (ii) learn magic values from infinite domains, such as the value of pi, and (iii) scale to domains with millions of constant symbols.