Expand description
A heterogeneous discovered law — either an EML-tree law from the differentiable core engine
or a rich-leaf affine/log-linear law from crate::affine.
The two engines deliberately use different representations (oxieml::EmlTree vs the affine
engine’s own ANode, because a·x+b / Σaᵢ ln xᵢ with negative coefficients is not a guarded
real EML form). AnySolution unifies them at the accuracy/complexity layer so both can live on
a single Pareto front and render through one path — which is what lets discover_auto_all (and the
CLI auto method) reach the affine engine by default. The affine engine is the one that
recovers product / power / ratio laws the shallow EML core can’t assemble, so the default search
must include it.
Enums§
- AnySolution
- A discovered law from either engine, exposing a common accuracy/complexity interface.
Functions§
- merge_
pareto - Pareto-filter a heterogeneous candidate set over (complexity, MSE) — discarding dominated and
near-duplicate members — then sort by MSE ascending (most accurate first). Mirrors
crate::pareto::ParetoFront::from_candidatesbut overAnySolution.