- author = "F. O. {de Franca} and M. Virgolin and M. Kommenda and M. S. Majumder and M. Cranmer and G. Espada and L. Ingelse and A. Fonseca and M. Landajuela and B. Petersen and R. Glatt and N. Mundhenk and C. S. Lee and J. D. Hochhalter and D. L. Randall and P. Kamienny and H. Zhang and G. Dick and A. Simon and B. Burlacu and Jaan Kasak and Meera Machado and Casper Wilstrup and W. G. {La Cava}",
- title = "{SRBench++}: Principled Benchmarking of Symbolic Regression With Domain-Expert Interpretation",
- journal = "IEEE Transactions on Evolutionary Computation",
- year = "2025",
- volume = "29",
- number = "4",
- pages = "1127--1137",
- month = aug,
- keywords = "genetic algorithms, genetic programming, XAI, Benchmark testing, Task analysis, Accuracy, Evolutionary computation, Prediction algorithms, Machine learning algorithms, Current measurement, Symbolic Regression, Competition, Interpretable Machine Learning",
- ISSN = "1089-778X",
-
URL = "
https://ir.cwi.nl/pub/34307/34307.pdf",
-
DOI = "
10.1109/TEVC.2024.3423681",
-
code_url = "
https://github.com/cavalab/srbench",
- size = "12 pages",
-
abstract = "... we propose and evaluate an approach to
benchmarking SR algorithms that addresses these
limitations of SRBench by 1) incorporating expert
evaluations of interpretability on a domain-specific
task, and 2) evaluating algorithms over distinct
properties of data science task.
... We evaluate 12 modern symbolic regression algorithms on thesebenchmarks and present an in-depth analysis of the results,discuss current challenges of symbolic regression algorithms and highlight possible improvements for the benchmark itself
operon, PS-Tree, gpzgd, QLattice, uDSR, Bingo, eql, pysr, geneticengine, E2ET, LinearRegression, TaylorGP, nsga-dcgp",
-
notes = "Also known as \cite{10586218}
See also \cite{defranca2023interpretablesymbolicregressiondata}
COVID-19 data in New York state, USA.",
