Struct SparseRMSprop 

pub struct SparseRMSprop { /* private fields */ }

Sparse RMSprop optimizer

Implements RMSprop optimization algorithm for sparse tensors with adaptive learning rates.

Implementations

impl SparseRMSprop

pub fn new( lr: f32, alpha: f32, eps: f32, weight_decay: f32, momentum: f32, centered: bool, ) -> Self

Create a new sparse RMSprop optimizer

pub fn default(lr: f32) -> Self

Create RMSprop optimizer with default settings

Trait Implementations

impl SparseOptimizer for SparseRMSprop

fn step( &mut self, parameters: &mut [&mut CsrTensor], gradients: &[&CsrTensor], ) -> TorshResult<()>

Update sparse parameters with sparse gradients

fn lr(&self) -> f32

Get current learning rate

fn set_lr(&mut self, lr: f32)

Set learning rate

fn zero_grad(&mut self)

Zero gradients (if applicable)