Crate drawset 

drawset: sampling and subset-selection primitives.

This crate is meant to be a low-level “sampling toolbox” that other crates can depend on without pulling in domain-specific machinery.

Exposed modules:

• reservoir: reservoir sampling (Algorithm L/R) + weighted reservoir.
• gumbel: Gumbel-max / Gumbel-top-k / relaxed k-hot.
• neighbor: simple neighborhood sampling helpers (useful for graph ML).
• qmc: quasi-Monte Carlo sequences (Sobol, Halton, Owen-scrambled Sobol).
• thinning: kernel thinning and herding (greedy coreset selection via MMD).

Re-exports

pub use gumbel::gumbel_max_sample;

pub use gumbel::gumbel_noise;

pub use gumbel::gumbel_softmax;

pub use gumbel::gumbel_topk_sample;

pub use gumbel::gumbel_topk_sample_with_rng;

pub use gumbel::relaxed_topk_gumbel;

pub use neighbor::NeighborSampler;

pub use reservoir::ReservoirSampler;

pub use reservoir::ReservoirSamplerR;

pub use reservoir::WeightedReservoirSampler;

pub use thinning::kernel_herd;

pub use thinning::kernel_thin;

pub use thinning::mmd_sq_from_gram;

Modules

gumbel

Gumbel-max sampling.

neighbor

Graph neighbor sampling.

qmc

Quasi-Monte Carlo sequences.

reservoir

Reservoir sampling.

thinning

Kernel thinning: coreset selection minimizing kernel discrepancy.

Structs

SobolGenerator

Incremental Sobol sequence generator using Gray-code enumeration.

Functions

halton_point

Compute a single Halton point in [0, 1)^d.

halton_sequence

Generate n Halton points in [0, 1)^d, starting from index = 1.

sobol_scrambled

Generate n Owen-scrambled Sobol points in [0, 1)^d.

sobol_sequence

Generate n Sobol points in [0, 1)^d, starting from index 1 (the origin at index 0 is skipped).