Enum LearningRateSchedule 

#[non_exhaustive]
pub enum LearningRateSchedule {
    Constant,
    Adaptive {
        factor: f64,
        patience: usize,
    },
    InvScaling {
        power: f64,
    },
}

Learning rate schedule for neural network training.

Controls how the learning rate changes over epochs.

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.

Constant

Fixed learning rate throughout training. Default.

Adaptive

Reduce learning rate by factor when loss plateaus for patience epochs.

Matches sklearn’s learning_rate='adaptive' behavior.

Fields

factor: f64

Multiplicative factor to reduce LR (default: 0.2).

patience: usize

Number of plateau epochs before reducing (default: 10).

InvScaling

Inverse scaling: lr(t) = initial_lr / t^power.

Fields

power: f64

Exponent for inverse scaling (default: 0.5).

Implementations

impl LearningRateSchedule

pub fn adaptive() -> Self

Adaptive schedule with sklearn-like defaults (factor=0.2, patience=10).

Trait Implementations

impl Clone for LearningRateSchedule

fn clone(&self) -> LearningRateSchedule

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for LearningRateSchedule

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

Formats the value using the given formatter.

impl Default for LearningRateSchedule

fn default() -> LearningRateSchedule

Returns the “default value” for a type.

impl PartialEq for LearningRateSchedule

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

impl StructuralPartialEq for LearningRateSchedule