Enum ParametricAlgorithm 

pub enum ParametricAlgorithm {
    Saem(SaemConfig),
}

The parametric algorithms supported by PMcore.

Use the constructors to select an algorithm with its default configuration:

use pmcore::prelude::*;

// Default SAEM configuration.
let algorithm = ParametricAlgorithm::saem();

To customize an algorithm, build its configuration struct (which exposes only the setters valid for that algorithm) and pass it directly to fit_with:

use pmcore::prelude::*;

// SAEM with a custom iteration schedule and seed.
let config = SaemConfig::new()
    .k1_iterations(500)
    .k2_iterations(200)
    .seed(42);
// `problem.fit_with(config)` accepts the config directly.

SaemConfig implements Algorithm by delegating to the matching enum variant, so configs can be passed to fit_with without converting them first.

Variants

Saem(SaemConfig)

Stochastic Approximation Expectation-Maximization.

Implementations

impl ParametricAlgorithm

pub fn saem() -> Self

The Stochastic Approximation Expectation-Maximization (SAEM) algorithm with its default configuration.

Trait Implementations

impl<E: Equation + Send + 'static> Algorithm<E, Parametric> for ParametricAlgorithm

type Output = ParametricResult<E>

The specific result struct (e.g. NonParametricResult<E>).

fn fit(self, _problem: EstimationProblem<E, Parametric>) -> Result<Self::Output>

Consumes the configuration and the problem, runs the optimization to completion, and returns the strictly-typed result.

impl Clone for ParametricAlgorithm

fn clone(&self) -> ParametricAlgorithm

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for ParametricAlgorithm

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

Formats the value using the given formatter.

impl Default for ParametricAlgorithm

fn default() -> Self

Returns the “default value” for a type.

impl From<SaemConfig> for ParametricAlgorithm

fn from(config: SaemConfig) -> Self

Converts to this type from the input type.