Struct GradientDescent 

pub struct GradientDescent {
    pub learning_rate: f64,
    pub max_iter: usize,
    pub tol: f64,
}

Gradient descent optimizer.

Fields

learning_rate: f64

Fixed learning rate.

max_iter: usize

Maximum number of iterations.

tol: f64

Convergence tolerance (on gradient norm).

Implementations

impl GradientDescent

pub fn new(lr: f64, max_iter: usize, tol: f64) -> Self

Create a new gradient descent optimizer.

pub fn backtracking_line_search<F: ConvexFunction>( f: &F, x: &[f64], grad: &[f64], ) -> f64

Backtracking line search satisfying the Armijo condition.

Returns a step size α such that f(x - α ∇f(x)) ≤ f(x) - c₁ α ‖∇f(x)‖².

pub fn minimize<F: ConvexFunction>( &self, f: &F, x0: &[f64], ) -> (Vec<f64>, f64, usize)

Minimize f starting from x0.

Returns (x_star, f(x_star), iterations).

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

Formats the value using the given formatter.