Enum Penalty 

#[non_exhaustive]
pub enum Penalty {
    None,
    L1,
    L2,
    ElasticNet(f64),
}

Regularization penalty for logistic regression.

Controls the type of regularization applied during training:

• None — no regularization
• L1 — Lasso penalty (promotes sparsity via proximal gradient descent)
• L2 — Ridge penalty (default, shrinks coefficients)
• ElasticNet(l1_ratio) — Mix of L1 and L2; l1_ratio ∈ [0, 1] where 1.0 = pure L1, 0.0 = pure L2

Solver compatibility

Penalty	GradientDescent	L-BFGS
None	✓	✓
L1	✓	✗ (error)
L2	✓	✓
ElasticNet	✓	✗ (error)

Variants (Non-exhaustive)

Non-exhaustive enums could have additional variants added in future. Therefore, when matching against variants of non-exhaustive enums, an extra wildcard arm must be added to account for any future variants.

None

No regularization.

L1

L1 (Lasso) penalty — promotes sparse coefficients.

L2

L2 (Ridge) penalty — shrinks all coefficients (default).

ElasticNet(f64)

Elastic Net — mix of L1 and L2. The f64 is the L1 ratio ∈ [0, 1].

Trait Implementations

impl Clone for Penalty

fn clone(&self) -> Penalty

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for Penalty

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl Default for Penalty

fn default() -> Penalty

Returns the “default value” for a type.

impl PartialEq for Penalty

fn eq(&self, other: &Penalty) -> bool

Tests for self and other values to be equal, and is used by ==.

fn ne(&self, other: &Rhs) -> bool

Tests for !=. The default implementation is almost always sufficient, and should not be overridden without very good reason.

impl StructuralPartialEq for Penalty