Struct GroupLassoRegularization 

pub struct GroupLassoRegularization {
    pub lambda: f64,
    pub group_size: usize,
}

Group Lasso regularization.

Encourages group-wise sparsity by penalizing the L2 norm of groups. Useful when features have natural groupings.

References

• Yuan & Lin (2006): “Model selection and estimation in regression with grouped variables”

Fields

lambda: f64

Regularization strength

group_size: usize

Group size (number of consecutive parameters per group)

Implementations

impl GroupLassoRegularization

pub fn new(lambda: f64, group_size: usize) -> Self

Create a new group lasso regularizer.

Trait Implementations

impl Clone for GroupLassoRegularization

fn clone(&self) -> GroupLassoRegularization

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for GroupLassoRegularization

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

Formats the value using the given formatter.

impl Default for GroupLassoRegularization

fn default() -> Self

Returns the “default value” for a type.

impl Regularizer for GroupLassoRegularization

fn compute_penalty( &self, parameters: &HashMap<String, Array<f64, Ix2>>, ) -> TrainResult<f64>

Compute the regularization penalty for given parameters.

fn compute_gradient( &self, parameters: &HashMap<String, Array<f64, Ix2>>, ) -> TrainResult<HashMap<String, Array<f64, Ix2>>>

Compute the gradient of the regularization penalty.