SR-DEC Examples

SR-DEC: Symbolic Regression with Discrete Exterior Calculus primitives.

This repository contains the scripts to reproduce the benchmark problems discussed in the paper Discovering interpretable physical models with symbolic regression and discrete exterior calculus.

Benchmark problems:

• Poisson equation

• Euler's Elastica

• Linear Elasticity

Installation

The dependencies are collected in environment.yaml and can be installed, after cloning the repository, using mamba:

$ mamba env create -f environment.yaml

Running the benchmarks

For each benchmark, run the corresponding main script (stgp_ + benchmark name), for example for Poisson:

$ python stgp_poisson.py poisson.yaml

Check the online documentation of Flex for the meaning of the configuration parameters included in the .yaml files.

Citing

@article{Manti_2024,
    doi = {10.1088/2632-2153/ad1af2},
    url = {https://dx.doi.org/10.1088/2632-2153/ad1af2},
    year = {2024},
    publisher = {IOP Publishing},
    volume = {5},
    number = {1},
    pages = {015005},
    author = {Simone Manti and Alessandro Lucantonio},
    title = {Discovering interpretable physical models using symbolic regression and discrete exterior calculus},
    journal = {Machine Learning: Science and Technology}
}