Exploring multi-view symbolic regression methods in physical sciences

Created by W.Langdon from gp-bibliography.bib Revision:1.8880

@Article{Russeil:2026:RSTA,

• author = "Etienne Russeil and Fabricio {Olivetti de Franca} and Guillaume Moinard and Konstantin Malanchev and Maxime Cherrey",
• title = "Exploring multi-view symbolic regression methods in physical sciences",
• journal = "Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences",
• year = "2026",
• volume = "384",
• number = "2317",
• pages = "20240592",
• month = "9 " # apr,
• keywords = "genetic algorithms, genetic programming, Operon, PySR, phi-SO, eggp, symbolic regression, interpretability, physical sciences, multi-dataset, artificial intelligence, AI, fluid mechanics, galaxies, mathematical modeling, observational astronomy",
• ISSN = "1364-503X",
• URL = "https://royalsocietypublishing.org/rsta/article-pdf/doi/10.1098/rsta.2024.0592/6131814/rsta.2024.0592.pdf",
• DOI = "10.1098/rsta.2024.0592",
• size = "16 pages",
• abstract = "Describing the worlds behaviour through mathematical functions helps scientists to achieve a better understanding of the inner mechanisms of different phenomena. Traditionally this is done by deriving new equations from first principles and careful observations. A modern alternative is to automate part of this process with symbolic regression (SR). The SR algorithms search for a function that adequately fits the observed data while trying to enforce sparsity, in the hopes of generating an interpretable equation. A particularly interesting extension to these algorithms is the multi-view symbolic regression (MvSR). It searches for a parametric function capable of describing multiple datasets generated by the same phenomena, which helps to mitigate the common problems of overfitting and data scarcity. Recently, multiple implementations added support to MvSR with small differences between them. we test and compare MvSR as supported in Operon, PySR, phi-SO and eggp, in different real-world datasets. We show that they all often achieve good accuracy while proposing solutions with only a few free parameters. However, we find that certain features enable a more frequent generation of better models. We conclude by providing guidelines for future MvSR developments.",
• notes = "part of the discussion meeting issue Symbolic regression in the physical sciences \cite{Bartlett:2026:RSTAintro}.",

}

Genetic Programming entries for Etienne Russeil Fabricio Olivetti de Franca Guillaume Moinard Konstantin Malanchev Maxime Cherrey

Citations