Zoetrope Genetic Programming for Regression

TL;DR

Zoetrope Genetic Programming (ZGP) introduces a novel representation for symbolic regression that constructs complex features through repeated fusion operations, achieving state-of-the-art results efficiently.

Contribution

The paper presents a new zoetropic representation for genetic programming in symbolic regression, improving performance and computational efficiency over existing methods.

Findings

ZGP achieves state-of-the-art performance on public regression datasets.

ZGP demonstrates lower computational time compared to other symbolic regression algorithms.

ZGP effectively constructs complex features through repeated fusion operations.

Abstract

The Zoetrope Genetic Programming (ZGP) algorithm is based on an original representation for mathematical expressions, targeting evolutionary symbolic regression.The zoetropic representation uses repeated fusion operations between partial expressions, starting from the terminal set. Repeated fusions within an individual gradually generate more complex expressions, ending up in what can be viewed as new features. These features are then linearly combined to best fit the training data. ZGP individuals then undergo specific crossover and mutation operators, and selection takes place between parents and offspring. ZGP is validated using a large number of public domain regression datasets, and compared to other symbolic regression algorithms, as well as to traditional machine learning algorithms. ZGP reaches state-of-the-art performance with respect to both types of algorithms, and demonstrates a low computational time compared to other symbolic regression approaches.