Enum RegularizationStrategy 

pub enum RegularizationStrategy {
    None,
    L1(Float),
    L2(Float),
    ElasticNet {
        alpha: Float,
        l1_ratio: Float,
    },
    GroupLasso {
        alpha: Float,
    },
    NuclearNorm {
        alpha: Float,
    },
    TaskClustering {
        n_clusters: usize,
        intra_cluster_alpha: Float,
        inter_cluster_alpha: Float,
    },
    TaskRelationship {
        relationship_strength: Float,
        similarity_threshold: Float,
    },
    MetaLearning {
        meta_learning_rate: Float,
        inner_learning_rate: Float,
        n_inner_steps: usize,
    },
}

Regularization strategies for multi-task learning

Variants

None

No regularization

L1(Float)

L1 regularization (Lasso)

L2(Float)

L2 regularization (Ridge)

ElasticNet

Elastic Net (L1 + L2)

Fields

alpha: Float

l1_ratio: Float

GroupLasso

Group Lasso

Fields

alpha: Float

NuclearNorm

Nuclear norm regularization

Fields

alpha: Float

TaskClustering

Task clustering regularization

Fields

n_clusters: usize

intra_cluster_alpha: Float

inter_cluster_alpha: Float

TaskRelationship

Task relationship learning

Fields

relationship_strength: Float

similarity_threshold: Float

MetaLearning

Meta-learning for multi-task

Fields

meta_learning_rate: Float

inner_learning_rate: Float

n_inner_steps: usize

Trait Implementations

impl Clone for RegularizationStrategy

fn clone(&self) -> RegularizationStrategy

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for RegularizationStrategy

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

Formats the value using the given formatter.

impl Default for RegularizationStrategy

fn default() -> RegularizationStrategy

Returns the “default value” for a type.

impl PartialEq for RegularizationStrategy

fn eq(&self, other: &RegularizationStrategy) -> 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 RegularizationStrategy