Standard Benchmark Optimization Functions

A set of standard benchmark optimization functions for R and a common interface to sample them.


Build Status codecov.io

A number of standard optimization functions for R along with sampling methods. There is a unified interface to sampling the functions. One can run sample.func("rosenbrok", n=250, k=5, method="lhs.sampling") to get a 250 sample Latin hypercube in 5D of the rosenbrock function.

Available functions

The following multi-D scalar functions are implemented. They are all defined on an arbitrary number of inputs.

  • ackley
  • rosenbrock
  • schwefel
  • sinc
  • spherical
  • zakharov

Sampling methods

The following sampling methods are supported with their internal names in parenthesis. With the exception of hexagonal.sample these are all defined on an arbitrary number of dimensions.

  • Latin hypercube (lh.sample)
  • Uniform random (random.sample)
  • Cartesian lattice (cartesian.sample)
  • Hexagonal lattice (hexagonal.sample)
  • Toroidal sampling (torus.sample)
  • Sobol sequence (sobol.sample)
  • Halton sequence (halton.sample)

News

Reference manual

It appears you don't have a PDF plugin for this browser. You can click here to download the reference manual.

install.packages("optim.functions")

0.1 by Thomas Torsney-Weir, 2 years ago


Browse source code at https://github.com/cran/optim.functions


Authors: Thomas Torsney-Weir [aut, cre]


Documentation:   PDF Manual  


MIT + file LICENSE license


Imports lhs, randtoolbox, stats, stringr

Suggests testthat, covr


See at CRAN