Learning with Data on Riemannian Manifolds

We provide a variety of algorithms for manifold-valued data, including Fréchet summaries, hypothesis testing, clustering, visualization, and other learning tasks. See Bhattacharya and Bhattacharya (2012) for general exposition to statistics on manifolds.

Riemann

Riemann is an R package for learning with data on Riemannian manifolds. In statistics and machine learning, the term manifold appears in two realms; one is dimensionality reduction where we assume that low-dimensional data manifold is embedded in high-dimensional Euclidean space. The other is statistics on manifolds - data lie on some Riemannian manifolds that we are already well aware of. Riemann aims to achieve the latter. If you are interested in dimension reduction, please check another R package Rdimtools.

Installation

• Option 1 : released version from CRAN.

install.packages("Riemann")

• Option 2 : development version from GitHub.

if (!require("devtools")) {
  install.packages("devtools")
}
devtools::install_github("kisungyou/Riemann")