Struct Nesterov 

pub struct Nesterov {
    pub l0: f64,
    pub t: f64,
    pub inertia: f64,
}

Nesterov accelerated gradient descent

Like accelerated gradient descent, Nesterov accelerated gradient descent includes a momentum term. In contrast to regular gradient descent, the acceleration is not calculated with respect to the current position, but to the estimated new one. Source: [G. Hinton’s lecture 6c] (http://www.cs.toronto.edu/~tijmen/csc321/slides/lecture_slides_lec6.pdf)

Fields

l0: f64

Start learning rate

t: f64

Smaller t will decrease the learning rate faster

After t events the start learning rate will be a half l0, after two t events the learning rate will be one third l0, and so on.

inertia: f64

To simulate friction, please select a value smaller than 1 (recommended)

Trait Implementations

impl Clone for Nesterov

fn clone(&self) -> Nesterov

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for Nesterov

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

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for Nesterov

fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Serialize for Nesterov

fn serialize<__S>(&self, __serializer: __S) -> Result<__S::Ok, __S::Error>

where __S: Serializer,

Serialize this value into the given Serde serializer.

impl<M> Teacher<M> for Nesterov

where M: Model, M::Target: Vector,

type Training = (usize, Vec<f64>)

Contains state which changes during the training, but is not part of the expertise

fn new_training(&self, model: &M) -> (usize, Vec<f64>)

Creates an instance holding all mutable state of the algorithm

fn teach_event<Y, C>( &self, training: &mut (usize, Vec<f64>), model: &mut M, cost: &C, features: &M::Features, truth: Y, )

where C: Cost<Y, M::Target>, Y: Copy,

Changes models coefficients so they minimize the cost function (hopefully)