Search papers, labs, and topics across Lattice.
DeepPySR is a novel symbolic regression framework that enhances the discovery of analytical equations from complex datasets by implementing a dynamic variable-pruning schedule, an exponential Pareto selection criterion, and a multi-layer architecture for hierarchical symbolic composition. This approach effectively addresses challenges such as high-dimensional inputs, multicollinearity, and class imbalance, leading to improved model interpretability and performance. On various benchmarks, DeepPySR significantly outperforms existing methods, yielding higher R虏 and F1 scores while producing interpretable formulas that align with relevant domain risk factors.
DeepPySR achieves superior performance in symbolic regression, yielding interpretable models that significantly outperform traditional methods in real-world scientific applications.
Symbolic regression (SR) discovers analytical equations from data, yielding glass-box models with directly interpretable formulas, unlike black-box methods that rely on unstable post-hoc tools such as SHAP or LIME. This transparency is crucial in clinical medicine and social science, but SR faces three challenges: high-dimensional inputs, principled selection of Pareto-front formulae, and data irregularities such as multicollinearity and class imbalance. We introduce DeepPySR, which addresses these issues with a dynamic variable-pruning schedule to remove irrelevant features during search, an exponential Pareto selection criterion that eliminates trade-offs between accuracy and complexity, and a multi-layer architecture for hierarchical symbolic composition. On four Feynman physics benchmarks and seven biomedical and social-science datasets, DeepPySR outperforms PySR and baselines on body fat (R$^2$: 0.794 vs.\ 0.702), heart disease (F1: 0.898 vs.\ 0.787), student performance (R$^2$: 0.964 vs.\ 0.948), and Raine BMI (R$^2$: 0.525 vs.\ 0.370), producing interpretable formulas aligned with domain risk factors.
