Struct OrthogonalRegularization 

pub struct OrthogonalRegularization {
    pub lambda: f64,
}

Orthogonal regularization.

Encourages weight matrices to be orthogonal: W^T * W ≈ I Helps prevent internal covariate shift and improves gradient flow.

References

• Brock et al. (2017): “Neural Photo Editing with Introspective Adversarial Networks”

Fields

lambda: f64

Regularization strength

Implementations

impl OrthogonalRegularization

pub fn new(lambda: f64) -> Self

Create a new orthogonal regularizer.

Trait Implementations

impl Clone for OrthogonalRegularization

fn clone(&self) -> OrthogonalRegularization

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for OrthogonalRegularization

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

Formats the value using the given formatter.

impl Default for OrthogonalRegularization

fn default() -> Self

Returns the “default value” for a type.

impl Regularizer for OrthogonalRegularization

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.