Struct SparseAdam 

pub struct SparseAdam { /* private fields */ }

Sparse Adam optimizer for handling sparse gradients efficiently.

Implementations

impl SparseAdam

pub fn new( learning_rate: f32, beta1: f32, beta2: f32, epsilon: f32, weight_decay: f32, config: SparseConfig, ) -> Self

pub fn with_default_config( learning_rate: f32, beta1: f32, beta2: f32, epsilon: f32, weight_decay: f32, ) -> Self

Trait Implementations

impl Debug for SparseAdam

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

Formats the value using the given formatter.

impl OptimizerState for SparseAdam

fn zero_grad(&mut self) -> Result<()>

Zero out gradients

fn step(&mut self, parameters: &mut [Tensor]) -> Result<()>

Perform optimization step

fn get_lr(&self) -> f32

Get current learning rate

fn set_lr(&mut self, lr: f32)

Set learning rate

fn state_dict(&self) -> Result<HashMap<String, Tensor>>

Save optimizer state to dictionary

fn load_state_dict(&mut self, state: HashMap<String, Tensor>) -> Result<()>

Load optimizer state from dictionary