Struct GradientDescent

pub struct GradientDescent {
    pub learning_rate: f64,
    pub max_iterations: usize,
    pub tolerance: Option<f64>,
}

Gradient descent optimizer. NOTE: Only for functions $f: \mathbb{R}^n \rightarrow \mathbb{R}$ for now. The gradient descent optimizer is an iterative algorithm that finds the local minimum of a function. The algorithm starts with an initial guess for the local minimum and moves iteratively in the direction of the negative gradient until the gradient is close to zero.

Fields

learning_rate: f64

Learning rate (aka. alpha or eta).

max_iterations: usize

Maximum number of iterations.

tolerance: Option<f64>

Tolerance for the gradient.

Implementations

impl GradientDescent

pub fn new( learning_rate: f64, max_iterations: usize, tolerance: Option<f64>, ) -> GradientDescent

Returns a new instance of the gradient descent optimizer.

Panics

Panics if tolerance is not positive.

pub fn optimize<F>( &self, f: F, x0: &[f64], verbose: bool, ) -> GradientDescentResult

where F: for<'v> Fn(&[Variable<'v>]) -> Variable<'v>,

Performs gradient descent optimization.

Trait Implementations

impl Clone for GradientDescent

fn clone(&self) -> GradientDescent

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for GradientDescent

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

Formats the value using the given formatter.

impl Default for GradientDescent

fn default() -> GradientDescent

Returns the “default value” for a type.