% Generated by roxygen2: do not edit by hand

% Please edit documentation in R/metrics.R

\name{sgdr}

\alias{sgdr}

\title{Stochastic Gradient Descent with Warm Restarts}

\usage{

sgdr(lrmin = 5e-10, lrmax = 0.05, restart = 50, mult = 1, epoch = NULL)

}

\arguments{

\item{lrmin}{Lower limit of the range for the learning rate.}

\item{lrmax}{Upper limit of the range for the learning rate.}

\item{restart}{Number of epochs until a restart is conducted.}

\item{mult}{Factor, by which the number of epochs until a restart is increased at every restart.}

\item{epoch}{Epoch, for which the learning rate shall be calculated.}

}

\value{

A numeric value.

}

\description{

Compute the learning Rate for a given epoch using Stochastic Gradient Descent with Warm Restarts. Implements approach from this \href{https://arxiv.org/abs/1608.03983}{paper}.

}

\examples{

sgdr(lrmin = 5e-10, lrmax = 5e-2, restart = 50,

mult = 1, epoch = 5)

}