Struct AdamW 

pub struct AdamW { /* private fields */ }

AdamW optimizer.

See:

• Decoupled Weight Decay Regularization, Loshchilov and Hutter, 2019.
• Cautious Weight Decay, 2025
• On the Convergence of Adam and Beyond

Configured by AdamWConfig.

Trait Implementations

impl Clone for AdamW

fn clone(&self) -> AdamW

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl<B: Backend> SimpleOptimizer<B> for AdamW

fn step<const D: usize>( &self, lr: LearningRate, tensor: Tensor<B, D>, grad: Tensor<B, D>, state: Option<Self::State<D>>, ) -> (Tensor<B, D>, Option<Self::State<D>>)

A single optimization step for any tensor that represents the parameters of a model.

type State<const D: usize> = AdamWState<B, D>

The state of the optimizer. It also implements record, so that it can be saved.

fn to_device<const D: usize>( state: Self::State<D>, device: &Device<B>, ) -> Self::State<D>

Change the device of the state.