Evolutional Math combines cross-validated R-squared fitness, island-model GP with operator-subset islands, structural deduplication, and L-BFGS-B constant refinement to recover compact ground-truth expressions with R² >= 0.99 on synthetic benchmarks and a 24-row clinical dataset.
Exhaustive symbolic regression,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.NE 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Evolutional Math: Cross-Validated Island-Model Genetic Programming for Interpretable Symbolic Regression on Small, Wide Datasets
Evolutional Math combines cross-validated R-squared fitness, island-model GP with operator-subset islands, structural deduplication, and L-BFGS-B constant refinement to recover compact ground-truth expressions with R² >= 0.99 on synthetic benchmarks and a 24-row clinical dataset.