Data Mining Algorithms In R/Packages/optimsimplex/optimsimplex-package

Description

edit

The goal of this package is to provide a building block for optimization algorithms based on a simplex. The 'optimsimplex package may be used in the following optimization methods:

  • the simplex method of Spendley et al.,
  • the method of Nelder and Mead,
  • the Box’s algorithm for constrained optimization,
  • the multi-dimensional search by Torczon,
  • etc ...

Features

edit

The following is a list of features currently provided:

  • Manage various simplex initializations
  • initial simplex given by user,
  • initial simplex computed with a length and along the coordinate axes,
  • initial regular simplex computed with Spendley et al. formula,
  • initial simplex computed by a small perturbation around the initial guess point,
  • initial simplex computed from randomized bounds.
  • sort the vertices by increasing function values,
  • compute the standard deviation of the function values in the simplex,
  • compute the simplex gradient with forward or centered differences,
  • shrink the simplex toward the best vertex,
  • etc...

Details

edit
Package: optimsimplex
Type: Package
Version: 1.0-2
Date: 2010-05-11
License: CeCILL-2
LazyLoad: yes

Authors

edit

Author of Scilab optimsimplex module: Michael Baudin (INRIA - Digiteo)
Author of R adaptation: Sebastien Bihorel (sb.pmlab@gmail.com)