Package implements Kernel-based Regularized Least Squares (KRLS), a machine learning method to fit multidimensional functions y=f(x) for regression and classification problems without relying on linearity or additivity assumptions. KRLS finds the best fitting function by minimizing the squared loss of a Tikhonov regularization problem, using Gaussian kernels as radial basis functions. For further details see Hainmueller and Hazlett (2014).

Author | Jens Hainmueller (Stanford) Chad Hazlett (UCLA) |

Date of publication | 2014-05-21 21:21:47 |

Maintainer | Jens Hainmueller <jhain@stanford.edu> |

License | GPL (>= 2) |

Version | 0.3-7 |

http://www.r-project.org | |

http://www.stanford.edu/~jhain/ |

**fdskrls:** Compute first differences with KRLS

**gausskernel:** Gaussian Kernel Distance Computation

**krls:** Kernel-based Regularized Least Squares (KRLS)

**lambdasearch:** Leave-one-out optimization to find lambda

**looloss:** Loss Function for Leave One Out Error

**plot.krls:** Plot method for Kernel-based Regularized Least Squares (KRLS)...

**predict.krls:** Predict method for Kernel-based Regularized Least Squares...

**solveforc:** Solve for Choice Coefficients in KRLS

**summary.krls:** Summary method for Kernel-based Regularized Least Squares...

KRLS

KRLS/NAMESPACE

KRLS/GPL-2

KRLS/R

KRLS/R/gausskernel.R
KRLS/R/looloss.R
KRLS/R/solveforc.R
KRLS/R/multdiag.R
KRLS/R/lambdasearch.r

KRLS/R/summary.krls.R
KRLS/R/predict.krls.R
KRLS/R/plot.krls.R
KRLS/R/zzz.r

KRLS/R/krls.R
KRLS/R/fdskrls.r

KRLS/MD5

KRLS/DESCRIPTION

KRLS/LICENSE.note

KRLS/man

KRLS/man/krls.Rd
KRLS/man/solveforc.Rd
KRLS/man/looloss.Rd
KRLS/man/fdskrls.Rd
KRLS/man/summary.krls.Rd
KRLS/man/lambdasearch.Rd
KRLS/man/plot.krls.Rd
KRLS/man/predict.krls.Rd
KRLS/man/gausskernel.Rd
KRLS/GPL-3

Questions? Problems? Suggestions? Tweet to @rdrrHQ or email at ian@mutexlabs.com.

All documentation is copyright its authors; we didn't write any of that.