el0ps.estimator.L0Estimator¶
- class el0ps.estimator.L0Estimator(datafit, penalty, lmbd, fit_intercept=False, solver=<el0ps.solver.bnb.BnbSolver object>)¶
Scikit-learn-compatible linear model estimators based on L0-regularized problems.
The estimator corresponds to a solution of the problem
\[\textstyle\min_{\mathbf{x} \in \mathbb{R}^{n}} f(\mathbf{Ax}) + \lambda\|\mathbf{x}\|_0 + h(\mathbf{x})\]where \(f\) is a datafit function, \(\mathbf{A} \in \mathbb{R}^{m \times n}\) is a matrix, \(\lambda > 0\) is a parameter, the L0-norm \(\|\cdot\|_0\) counts the number of non-zero entries in its input, and \(h\) is a penalty function.
- Parameters:
- datafit: BaseDatafit
Datafit function.
- penalty: BasePenalty
Penalty function.
- lmbd: float
L0-norm weight.
- fit_intercept: bool, default=False
Whether to fit an intercept term.
- solver: BaseSolver, default=BnbSolver()
Solver for the estimator associated problem.
- __init__(datafit, penalty, lmbd, fit_intercept=False, solver=<el0ps.solver.bnb.BnbSolver object>)¶
Methods
__init__(datafit, penalty, lmbd[, ...])fit(X, y)Fit model.
get_metadata_routing()Get metadata routing of this object.
get_params([deep])Get parameters for this estimator.
predict(X)Predict using the linear model.
set_params(**params)Set the parameters of this estimator.