Function sample_exponential_batch 

pub fn sample_exponential_batch<F>(
    n: usize,
    rate: F,
    seed: Option<u64>,
) -> StatsResult<Array1<F>>
where
    F: Float + NumCast + SimdUnifiedOps + SampleUniform,

Generate n independent samples from Exp(rate) using a SIMD-accelerated inverse-CDF transform.

The CDF of Exp(λ) is F(x) = 1 − e^(−λx), so the inverse is:

x = −ln(u) / λ

where u ~ U(0, 1). The vectorised ln from scirs2_core is applied to the entire batch at once.

Arguments

• n — Number of samples.
• rate — Rate parameter λ (must be positive; mean = 1/λ).
• seed — Optional RNG seed.

Errors

Returns StatsError::InvalidArgument when n == 0 or rate <= 0.

Examples

use scirs2_stats::sample_exponential_batch;

let rate = 2.0_f64;
let samples = sample_exponential_batch::<f64>(1_000, rate, Some(99))
    .expect("sampling failed");
assert_eq!(samples.len(), 1_000);

// Empirical mean should be near 1/rate = 0.5
let mean: f64 = samples.sum() / samples.len() as f64;
assert!((mean - 0.5).abs() < 0.08);