Struct compute::optimize::optimizers::SGD

pub struct SGD { /* fields omitted */ }

Implements the Stochastic Gradient Descent optimizer with (Nesterov) momentum.

Implementations

impl SGD

pub fn new(
    stepsize: f64,
    momentum: f64,
    nesterov: bool,
    batchsize: usize
) -> Self

Create a new SGD optimizer.

stepsize: step size momentum: momentum factor nesterov: whether to use Nesterov momentum batchsize: size of each mini-batch

Trait Implementations

impl Clone for SGD

fn clone(&self) -> SGD

Returns a copy of the value.

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

Performs copy-assignment from source.

impl Debug for SGD

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

Formats the value using the given formatter.

impl Default for SGD

fn default() -> Self

Returns the “default value” for a type.

impl Optimizer for SGD

fn optimize<F>(
    &self,
    xs: &[f64],
    ys: &[f64],
    f: F,
    parameters: &[f64],
    maxsteps: usize
) -> Vec<f64> where
    F: Fn(&[F1]) -> F1 + Copy, 

Run the optimization algorithm, given a vector of parameters to optimize and a function which calculates the residuals.

fn grad_fn_type(&self) -> GradFn

impl Copy for SGD