gemseo.mlearning.linear_model_fitting.omp_cv module#

Scikit-learn Orthogonal Matching Pursuit (OMP) algorithm with build-in cross-validation.

class OrthogonalMatchingPursuitCV(settings=None)[source]#

Scikit-learn Orthogonal Matching Pursuit (OMP) algorithm with build-in cross-validation.

Given the linear model fitting problem presented in this page, this algorithm solves a penalized least squares problem of the form:

\[\min_w \|Xw-y\|_2^2 \quad \text{s.t.} \quad \|w\|_0\leq \eta\]

where \(\eta\) is a specific number of non-zero components of \(w\).

Alternatively:

\[\min_w \|w\|_0 \quad \text{s.t.} \quad \|Xw-y\|_2^2\leq \tau\]

where \(\tau\) is a specific model error.

Initialize self. See help(type(self)) for accurate signature.

Parameters:: settings (SettingsType | None) -- The settings of the linear model fitting algorithm. If None, use a default instance of Settings.