Optimizer

class empulse.optimizers.Optimizer

Abstract base class for all logit model optimizers.

Parameters:

objectiveLogitObjective

Prepared objective exposing logit_loss, logit_gradient, and logit_loss_gradient methods.

Xndarray of shape (n_samples, n_features)

Feature matrix (used only to determine the number of parameters).

Returns:

resultscipy.optimize.OptimizeResult

Optimization result with at least the following fields:

• x – final weight vector

• fun – final loss value

• nit – number of iterations performed

• success – True if a convergence criterion was met

• message – human-readable status string

abstractmethod __call__(objective, X, **kwargs)

Run the optimization and return an OptimizeResult.