Struct wyrm::optim::SGD

pub struct SGD { /* fields omitted */ }

Standard stochastic gradient descent optimizer with a fixed learning rate.

Methods

impl SGD

pub fn new() -> Self

Create a new optimizer instance with a given set of parameters.

pub fn learning_rate(self, learning_rate: f32) -> Self

Set the learning rate.

pub fn clamp(self, min: f32, max: f32) -> Self

Set the clamp bounds.

Trait Implementations

impl Default for SGD

fn default() -> Self

Returns the "default value" for a type.

impl Optimizer for SGD

fn step(&self, parameters: &[Variable<ParameterNode>])

Perform a single SGD step.