Struct SparseAdam 

pub struct SparseAdam { /* private fields */ }

Sparse Adam optimizer

A variant of Adam that handles sparse gradients more efficiently by only updating the parameters that have non-zero gradients.

Implementations

impl SparseAdam

pub fn new( params: Vec<Arc<RwLock<Tensor>>>, lr: Option<f32>, beta1: Option<f32>, beta2: Option<f32>, eps: Option<f32>, weight_decay: Option<f32>, ) -> Self

Create a new SparseAdam optimizer

Arguments

• params - Parameters to optimize
• lr - Learning rate (default: 1e-3)
• beta1 - First moment decay rate (default: 0.9)
• beta2 - Second moment decay rate (default: 0.999)
• eps - Small constant for numerical stability (default: 1e-8)
• weight_decay - Weight decay (L2 penalty) (default: 0.0)

Trait Implementations

impl Optimizer for SparseAdam

fn step(&mut self) -> OptimizerResult<()>

Perform a single optimization step

fn zero_grad(&mut self)

Zero all gradients

fn get_lr(&self) -> Vec<f32>

Get the current learning rate

fn set_lr(&mut self, lr: f32)

Set one learning rate for every parameter group (broadcast).

fn add_param_group( &mut self, params: Vec<Arc<RwLock<Tensor>>>, options: HashMap<String, f32>, )

Add a parameter group

fn parameters(&self) -> Vec<Arc<RwLock<Tensor>>>

Get the parameter tensors managed by this optimizer.

fn state_dict(&self) -> OptimizerResult<OptimizerState>

Get state dict for serialization

fn load_state_dict(&mut self, state: OptimizerState) -> OptimizerResult<()>

Load state dict

fn set_lrs(&mut self, lrs: &[f32])

Set the learning rate of each parameter group individually.