Struct MultinomialFitInputs 

pub struct MultinomialFitInputs<'a> {
    pub design: ArrayView2<'a, f64>,
    pub y_one_hot: ArrayView2<'a, f64>,
    pub penalty: ArrayView2<'a, f64>,
    pub lambdas: ArrayView1<'a, f64>,
    pub row_weights: Option<ArrayView1<'a, f64>>,
    pub fisher_w_override: Option<ArrayView3<'a, f64>>,
    pub max_iter: usize,
    pub tol: f64,
}

Inputs to fit_penalized_multinomial.

The penalty matrix S is shared across classes; per-class smoothing parameters lambdas (length K - 1) scale S independently for each active class. The full block-replicated penalty is diag_a(λ_a) ⊗ S, which is exactly what gam_solve::arrow_schur::KroneckerPenaltyOp expresses in matrix-free form when this driver is later lifted into the arrow-Schur loop.

Fields

design: ArrayView2<'a, f64>

Design matrix X ∈ ℝ^{N×P} (one row per observation).

y_one_hot: ArrayView2<'a, f64>

Categorical response Y ∈ ℝ^{N×K}. Each row must be a point on the probability simplex (y_c ≥ 0, Σ_c y_c = 1): a one-hot indicator for hard classification, or a label-smoothed probability vector. Rows whose mass departs from 1 are rejected — the softmax residual gradient and Fisher block are the derivatives of Σ_c y_c log p_c only under the simplex constraint (see validate_multinomial_simplex).

penalty: ArrayView2<'a, f64>

Shared smoothing penalty S ∈ ℝ^{P×P} (symmetric, PSD).

lambdas: ArrayView1<'a, f64>

Per-active-class smoothing parameter λ_a (length K - 1).

row_weights: Option<ArrayView1<'a, f64>>

Optional per-row weights (length N); None ⇒ uniform 1.0.

fisher_w_override: Option<ArrayView3<'a, f64>>

Optional per-row Fisher-block override, shape (N, K-1, K-1) in the active-class gauge (the reference class K-1 is dropped). When Some, each Newton step uses this block as the curvature W in place of the analytic softmax Fisher w_n (δ_ab p_a − p_a p_b); the gradient/residual path stays analytic, so this is a curvature-only override (the research escape-hatch for latent multinomial fits, issue #349). Each per-row block must be symmetric, PSD, and finite — preconditions the FFI boundary discharges before constructing this view.

max_iter: usize

Maximum Newton iterations; recommend 50.

tol: f64

Relative-step convergence tolerance; recommend 1e-7.

Trait Implementations

impl<'a> Clone for MultinomialFitInputs<'a>

fn clone(&self) -> MultinomialFitInputs<'a>

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl<'a> Debug for MultinomialFitInputs<'a>

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

Formats the value using the given formatter.