Struct VlmdParams 

pub struct VlmdParams {
    pub num_modes: usize,
    pub num_latents: Option<usize>,
    pub alpha: f64,
    pub reg_lambda: f64,
    pub reg_rho: f64,
    pub tau: f64,
    pub tolerance: f64,
    pub max_iterations: usize,
}

Defaults follow the reference implementation.

Fields

num_modes: usize

Number of modes K.

num_latents: Option<usize>

Number of latent components L (at most the number of channels). None uses one per channel.

alpha: f64

Bandwidth penalty α: larger values give narrower modes.

reg_lambda: f64

Sparsity λ of the loadings, on the reference scale (see lasso).

reg_rho: f64

ADMM penalty ρ: how closely the latent components must equal the sum of their modes.

tau: f64

Dual step τ in [0, 1].

tolerance: f64

Stop when Σ((ωₙ₊₁ − ωₙ)/ωₙ)² falls to this.

max_iterations: usize

Implementations

impl VlmdParams

pub fn new(num_modes: usize) -> Self

Trait Implementations

impl Clone for VlmdParams

fn clone(&self) -> VlmdParams

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for VlmdParams

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

Formats the value using the given formatter.

impl PartialEq for VlmdParams

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