Struct QuasiRandomRBFSampler 

pub struct QuasiRandomRBFSampler<State = Untrained> {
    pub gamma: Float,
    pub n_components: usize,
    pub sequence_type: QuasiRandomSequence,
    pub random_state: Option<u64>,
    /* private fields */
}

Quasi-random RBF sampler using low-discrepancy sequences

This sampler generates random Fourier features for RBF kernels using quasi-random sequences instead of pseudo-random numbers, providing better uniform coverage of the frequency space and improved approximation quality.

Mathematical Background

For an RBF kernel k(x,y) = exp(-γ||x-y||²), the random Fourier features are: z(x) = √(2/n_components) * [cos(ω₁ᵀx + b₁), …, cos(ωₙᵀx + bₙ)]

Where ω ~ N(0, 2γI) and b ~ Uniform[0, 2π]. Using quasi-random sequences for generating ω and b provides better approximation properties.

Examples

use sklears_kernel_approximation::{QuasiRandomRBFSampler, QuasiRandomSequence};
use sklears_core::traits::{Transform, Fit, Untrained}
use scirs2_core::ndarray::array;

let x = array![[1.0, 2.0], [3.0, 4.0], [5.0, 6.0]];
let sampler = QuasiRandomRBFSampler::new(100)
    .gamma(1.0)
    .sequence_type(QuasiRandomSequence::Sobol);
let fitted = sampler.fit(&x, &()).unwrap();
let features = fitted.transform(&x).unwrap();
assert_eq!(features.shape(), &[3, 100]);

QuasiRandomRBFSampler

Fields

gamma: Float

RBF kernel parameter

n_components: usize

Number of Monte Carlo samples

sequence_type: QuasiRandomSequence

Quasi-random sequence type

random_state: Option<u64>

Random seed for reproducibility

Implementations

impl QuasiRandomRBFSampler<Untrained>

pub fn new(n_components: usize) -> Self

Create a new quasi-random RBF sampler

Arguments

• n_components - Number of Monte Carlo samples (random features)

pub fn gamma(self, gamma: Float) -> Self

Set the gamma parameter for the RBF kernel

pub fn sequence_type(self, sequence_type: QuasiRandomSequence) -> Self

Set the quasi-random sequence type

pub fn random_state(self, seed: u64) -> Self

Set the random state for reproducibility

Trait Implementations

impl<State: Clone> Clone for QuasiRandomRBFSampler<State>

fn clone(&self) -> QuasiRandomRBFSampler<State>

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl<State: Debug> Debug for QuasiRandomRBFSampler<State>

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

Formats the value using the given formatter.

impl Fit<ArrayBase<OwnedRepr<f64>, Dim<[usize; 2]>>, ()> for QuasiRandomRBFSampler<Untrained>

type Fitted = QuasiRandomRBFSampler<Trained>

The fitted model type

fn fit(self, x: &Array2<Float>, _y: &()) -> Result<Self::Fitted>

Fit the model to the provided data with validation

fn fit_with_validation( self, x: &X, y: &Y, _x_val: Option<&X>, _y_val: Option<&Y>, ) -> Result<(Self::Fitted, FitMetrics), SklearsError>

where Self: Sized,

Fit with custom validation and early stopping

impl Transform<ArrayBase<OwnedRepr<f64>, Dim<[usize; 2]>>> for QuasiRandomRBFSampler<Trained>

fn transform(&self, x: &Array2<Float>) -> Result<Array2<Float>>

Transform the input data