A Fast and Versatile SVM Package

Support vector machines (SVMs) and related kernel-based learning algorithms are a well-known class of machine learning algorithms, for non-parametric classification and regression. liquidSVM is an implementation of SVMs whose key features are: fully integrated hyper-parameter selection, extreme speed on both small and large data sets, full flexibility for experts, and inclusion of a variety of different learning scenarios: multi-class classification, ROC, and Neyman-Pearson learning, and least-squares, quantile, and expectile regression.

liquidSVM is a package written in C++ that provides SVM-type solvers for various classification and regression tasks. Because of a fully integrated hyper-parameter selection, very carefully implemented solvers, multi-threading and GPU support, and several built-in data decomposition strategies it provides unprecedented speed for small training sizes as well as for data sets of tens of millions of samples.

You can use it e.g. for multi-class classification, least squares (kernel) regression, or even quantile regression, etc.:

model <- mcSVM(Species ~ ., iris)
predict(model, iris)
model <- lsSVM(Height ~ ., trees)
y <- predict(model, trees)
model <- svmQuantileRegression(Height ~ ., trees)
y <- test(model, trees)

If you install build the package to be used on several machines please use the following:

install.packages("liquidSVM", configure.args="generic")

For details please look at the vignettes demo and documentation. Also check the help ?liquidSVM and ?svm. For the command-line version and other bindings go to (http://www.isa.uni-stuttgart.de/software/).


Reference manual

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


1.2.4 by Philipp Thomann, 5 months ago


Browse source code at https://github.com/cran/liquidSVM

Authors: Ingo Steinwart , Philipp Thomann

Documentation:   PDF Manual  

AGPL-3 license

Depends on methods

Suggests knitr, rmarkdown, deldir, testthat

Enhances mlr, ParamHelpers

See at CRAN