Struct GaussianPrior 

pub struct GaussianPrior { /* private fields */ }

Independent Gaussian N(mean, std²) prior on every real coordinate.

Implementations

impl GaussianPrior

pub fn new(mean: f64, std: f64, dim: usize) -> Self

I.i.d. Gaussian prior with the given per-coordinate mean/std over dim coordinates. std must be positive.

Trait Implementations

impl Clone for GaussianPrior

fn clone(&self) -> GaussianPrior

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for GaussianPrior

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

Formats the value using the given formatter.

impl GenomePrior for GaussianPrior

type Genome = RealVector

The genome type this prior generates.

fn model(&self) -> Model<RealVector>

The generative program p(x).

fn trace_of(&self, genome: &Self::Genome) -> Trace

Encode a genome as a trace under this prior’s address scheme — the inverse direction of running Self::model. The default delegates to the genome’s canonical TraceGenome::to_trace encoding, which is correct whenever the prior samples exactly the canonical sites (all the vector priors here). Priors with their own generative scheme — e.g. ArithmeticGrammarPrior’s tree-path grammar — override this so that scoring, weighted traces, and chain warm-starts work for any genome the prior can express.