Relational program synthesis with numerical reasoning

10/03/2022
by   Céline Hocquette, et al.
0

Program synthesis approaches struggle to learn programs with numerical values. An especially difficult problem is learning continuous values over multiple examples, such as intervals. To overcome this limitation, we introduce an inductive logic programming approach which combines relational learning with numerical reasoning. Our approach, which we call NUMSYNTH, uses satisfiability modulo theories solvers to efficiently learn programs with numerical values. Our approach can identify numerical values in linear arithmetic fragments, such as real difference logic, and from infinite domains, such as real numbers or integers. Our experiments on four diverse domains, including game playing and program synthesis, show that our approach can (i) learn programs with numerical values from linear arithmetical reasoning, and (ii) outperform existing approaches in terms of predictive accuracies and learning times.

READ FULL TEXT
research
08/05/2022

Learning programs with magic values

A magic value in a program is a constant symbol that is essential for th...
research
06/01/2019

Synthesizing Datalog Programs using Numerical Relaxation

The problem of learning logical rules from examples arises in diverse fi...
research
08/18/2023

Learning MDL logic programs from noisy data

Many inductive logic programming approaches struggle to learn programs f...
research
06/01/2022

Learning programs by combining programs

The goal of inductive logic programming is to induce a set of rules (a l...
research
01/18/2023

Generalisation Through Negation and Predicate Invention

The ability to generalise from a small number of examples is a fundament...
research
04/21/2020

Learning large logic programs by going beyond entailment

A major challenge in inductive logic programming (ILP) is learning large...
research
09/18/2023

Algebra of Self-Replication

Typical arguments for results like Kleene's Second Recursion Theorem and...

Please sign up or login with your details

Forgot password? Click here to reset