Enum CompressionStrategy 

pub enum CompressionStrategy {
    KnowledgeDistillation,
    EnsemblePruning,
    Quantization,
    WeightSharing,
    LowRankApproximation,
    SparseRepresentation,
    HierarchicalCompression,
    BayesianOptimization,
}

Compression strategy enumeration

Variants

KnowledgeDistillation

Knowledge distillation - train a smaller model to mimic ensemble

EnsemblePruning

Ensemble pruning - remove redundant or weak models

Quantization

Model quantization - reduce precision of model parameters

WeightSharing

Weight sharing - share parameters across models

LowRankApproximation

Low-rank approximation - approximate weight matrices

SparseRepresentation

Sparse representation - remove near-zero weights

HierarchicalCompression

Hierarchical compression - compress at multiple levels

BayesianOptimization

Bayesian optimization for ensemble size optimization

Trait Implementations

impl Clone for CompressionStrategy

fn clone(&self) -> CompressionStrategy

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for CompressionStrategy

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

Formats the value using the given formatter.

impl PartialEq for CompressionStrategy

fn eq(&self, other: &CompressionStrategy) -> bool

Tests for self and other values to be equal, and is used by ==.

fn ne(&self, other: &Rhs) -> bool

Tests for !=. The default implementation is almost always sufficient, and should not be overridden without very good reason.

impl Copy for CompressionStrategy

impl StructuralPartialEq for CompressionStrategy