Logistic-Gated Operators Enable Auditable Unit-Aware Thresholds in Symbolic Regression
This enables symbolic regression to produce compact, auditable equations with explicit thresholds for clinical applications, turning interpretability into a modeling constraint for governance-ready deployment.
The paper tackles the problem of encoding unit-aware thresholds and conditional logic in symbolic regression by proposing logistic-gated operators, which recover clinically plausible cut-points with 71% of thresholds within 10% of guideline anchors and use fewer gates than soft variants while maintaining competitive accuracy.
Symbolic regression promises readable equations but struggles to encode unit-aware thresholds and conditional logic. We propose logistic-gated operators (LGO) -- differentiable gates with learnable location and steepness -- embedded as typed primitives and mapped back to physical units for audit. Across two primary health datasets (ICU, NHANES), the hard-gate variant recovers clinically plausible cut-points: 71% (5/7) of assessed thresholds fall within 10% of guideline anchors and 100% within 20%, while using far fewer gates than the soft variant (ICU median 4.0 vs 10.0; NHANES 5.0 vs 12.5), and remaining within the competitive accuracy envelope of strong SR baselines. On predominantly smooth tasks, gates are pruned, preserving parsimony. The result is compact symbolic equations with explicit, unit-aware thresholds that can be audited against clinical anchors -- turning interpretability from a post-hoc explanation into a modeling constraint and equipping symbolic regression with a practical calculus for regime switching and governance-ready deployment.