Struct ChebyshevScalarization 

pub struct ChebyshevScalarization<M> {
    pub objectives: M,
    pub sharpness: f64,
    pub ideal: Vec<f64>,
    pub weight: Option<Vec<f64>>,
}

The Chebyshev (weighted-max) scalarization likelihood with a latent weight vector:

    w ~ Uniform(simplex)
    π_β(x, w) ∝ p(x) · exp(−β · s · max_i  w_i · (f_i(x) − z_i))

where z is the ideal point (a reference component-wise ≤ the objective values of interest, e.g. per-objective minima or a slightly optimistic estimate). Minimizing the weighted Chebyshev norm over x reaches every weakly Pareto-optimal point as w varies over the simplex (Miettinen 1999) — in particular the non-convex front regions where a weighted sum’s interior stationary point is a maximum and all its mass collapses onto the front’s endpoints. Use this when the front may be non-convex; use ParetoScalarization when it is known convex (the weighted sum is smoother).

Fields

objectives: M

The multi-objective fitness (objectives minimized).

sharpness: f64

Sharpness of the scalarized likelihood (see ParetoScalarization).

ideal: Vec<f64>

The ideal/reference point z (one entry per objective).

weight: Option<Vec<f64>>

None: the weight is a latent site (subject to the marginal-tilt caveat in the module docs). Some(w): a fixed weight — the posterior concentrates on that weight’s own front point, which is the mode to use for sweeping the front uniformly.

Implementations

impl<M> ChebyshevScalarization<M>

pub fn new(objectives: M, sharpness: f64, ideal: Vec<f64>) -> Self

Create a Chebyshev-scalarization likelihood with a latent weight.

pub fn with_weight(self, weight: Vec<f64>) -> Self

Fix the scalarization weight (front-sweeping mode): the posterior targets this weight’s own scalarized optimum — reaching interior points of non-convex fronts that no weighted sum can select.

Trait Implementations

impl<M: Clone> Clone for ChebyshevScalarization<M>

fn clone(&self) -> ChebyshevScalarization<M>

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl<G, M> GenomeLikelihood<G> for ChebyshevScalarization<M>

where G: 'static, M: MultiObjectiveFitness<G> + Clone + Send + Sync + 'static,

fn model(&self, genome: &G, beta: f64) -> Model<()>

The observation program conditioned on genome, at likelihood temperature beta.