Enum OptimizerKind 

#[non_exhaustive]
pub enum OptimizerKind {
    Sgd {
        momentum: f64,
        nesterov: bool,
    },
    Adam {
        beta1: f64,
        beta2: f64,
        epsilon: f64,
    },
}

Available optimizer algorithms.

Variants (Non-exhaustive)

Non-exhaustive enums could have additional variants added in future. Therefore, when matching against variants of non-exhaustive enums, an extra wildcard arm must be added to account for any future variants.

Sgd

Stochastic gradient descent with optional Nesterov momentum.

Fields

momentum: f64

Momentum coefficient (0.0 = no momentum). Default: 0.9.

nesterov: bool

Use Nesterov accelerated gradient. Default: true.

Adam

Adaptive moment estimation (Adam).

Defaults: β₁=0.9, β₂=0.999, ε=1e-8.

Fields

beta1: f64

Exponential decay rate for first moment. Default: 0.9.

beta2: f64

Exponential decay rate for second moment. Default: 0.999.

epsilon: f64

Small constant for numerical stability. Default: 1e-8.

Implementations

impl OptimizerKind

pub fn sgd() -> Self

SGD with default momentum (0.9, Nesterov).

Trait Implementations

impl Clone for OptimizerKind

fn clone(&self) -> OptimizerKind

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for OptimizerKind

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

Formats the value using the given formatter.

impl Default for OptimizerKind

fn default() -> Self

Returns the “default value” for a type.

impl PartialEq for OptimizerKind

fn eq(&self, other: &OptimizerKind) -> 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 OptimizerKind

impl StructuralPartialEq for OptimizerKind