Struct MultinomialFitOutputs 

pub struct MultinomialFitOutputs {
    pub coefficients_active: Array2<f64>,
    pub fitted_probabilities: Array2<f64>,
    pub iterations: usize,
    pub converged: bool,
    pub penalized_neg_log_likelihood: f64,
    pub deviance: f64,
    pub coefficient_covariance: Array2<f64>,
}

Outputs of fit_penalized_multinomial.

Fields

coefficients_active: Array2<f64>

Active-class coefficient block, shape (P, K-1) (column a is β_a). The reference class K - 1 has β_{K-1} ≡ 0 by construction and is not stored.

fitted_probabilities: Array2<f64>

Fitted probabilities, shape (N, K).

iterations: usize

Number of Newton iterations executed (including the final step that satisfied the tolerance).

converged: bool

true if the relative-step test was satisfied; false if the solver exhausted max_iter. (A non-converged solve is still returned; the caller decides whether to escalate.)

penalized_neg_log_likelihood: f64

Penalized negative log-likelihood at the returned β̂: −log L(β̂) + ½ Σ_a λ_a · β̂_a^T S β̂_a.

deviance: f64

Unpenalized deviance −2 log L(β̂) for diagnostic reporting.

coefficient_covariance: Array2<f64>

Joint Laplace posterior coefficient covariance H⁻¹ at the converged β̂, shape (P·(K−1))×(P·(K−1)) (#1101). Block-ordered to match the stacked active-class coefficient vector β = [β_0; …; β_{K-2}]: active class a’s P coefficients occupy rows/cols a·P .. (a+1)·P, indexed θ[a·P + i] = β̂[i, a]. This is the Laplace covariance from the factored penalized Hessian XᵀWX + diag_a(λ_a)⊗S; it drives the delta-method per-class probability standard errors (Self::predict_probabilities_with_se) on the fixed-λ inner-solve path.

Implementations

impl MultinomialFitOutputs

pub fn n_active_classes(&self) -> usize

Number of active classes M = K − 1 (columns of Self::coefficients_active).

pub fn p_per_class(&self) -> usize

Per-class coefficient dimension P (rows of Self::coefficients_active).

pub fn predict_probabilities_with_se( &self, x_new: ArrayView2<'_, f64>, ) -> Result<(Array2<f64>, Array2<f64>), EstimationError>

Evaluate softmax(X·β̂) AND its delta-method per-class probability standard error at fresh design rows X_new (#1101), using the joint Laplace covariance Self::coefficient_covariance.

The softmax Jacobian is ∂p_c/∂η_b = p_c (δ_{cb} − p_b) for active class b ∈ 0..M, and ∂η_b/∂β[i,a] = X[i]·δ_{ab}, so the gradient of the class-c probability w.r.t. the block-ordered coefficient vector is g_c[a·P + i] = X[i]·p_c (δ_{ca} − p_a) (the reference class M contributes only through −p_a in every active block). The delta-method variance is Var(p_c) = g_cᵀ Σ g_c with Σ = H⁻¹, and SE(p_c) = √Var(p_c). Returns (probs (N,K), prob_se (N,K)). X_new must have P columns (the same design basis used at fit time); its row count sets N. The SE is unclamped (the interval consumer applies the simplex [0,1] clamp).

Trait Implementations

impl Clone for MultinomialFitOutputs

fn clone(&self) -> MultinomialFitOutputs

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for MultinomialFitOutputs

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

Formats the value using the given formatter.