mmtsne (version 0.1.0)

mmtsneP: Multiple maps t-SNE with symmetric probability matrix

Description

mmtsneP estimates a multiple maps t-distributed stochastic neighbor embedding (multiple maps t-SNE) model.

Usage

mmtsneP(P, no_maps, no_dims = 2, max_iter = 500, momentum = 0.5,
  final_momentum = 0.8, mom_switch_iter = 250, eps = 1e-07)

Arguments

P

An \(N x N\) symmetric joint probability distribution matrix. These can be constructed from an \(N\) by \(D\) matrix with x2p and p2sp. Alternatively, the wrapper function mmtsne will wrap the matrix construction and multiple maps t-SNE model estimation into a single step.

no_maps

The number of maps (positive whole number) to be estimated.

no_dims

The number of dimensions per map. Typical values are 2 or 3.

max_iter

The number of iterations to run.

momentum

Constant scaling factor for update momentum in gradient descent algorithm.

final_momentum

Constant scaling factor for update momentum in gradient descent algorithm after the momentum switch point.

mom_switch_iter

The iteration at which momentum switches from momentum to final_momentum.

eps

A small positive value near zero.

Value

A list that includes the following objects:

Y

An N x no_dims x no_maps array of predicted coordinates.

weights

An N x no_maps matrix of unscaled weights. A high weight on entry \(i, j\) indicates a greater contribution of point \(i\) on map \(j\).

proportions

An N x no_maps matrix of scaled weights. A high weight on entry \(i, j\) indicates a greater contribution of point \(i\) on map \(j\).

Details

This code is an almost direct port of the original multiple maps t-SNE Matlab code by van der Maaten and Hinton (2012). mmtsne estimates a multidimensional array of N x no_dims x no_maps. Each map is an N x no_dims matrix of estimated t-SNE coordinates. When no_maps=1, multiple maps t-SNE reduces to standard t-SNE.

References

L.J.P. van der Maaten and G.E. Hinton. ``Visualizing Non-Metric Similarities in Multiple Maps.'' Machine Learning 87(1):33-55, 2012. PDF.

Examples

# NOT RUN {
# Load the iris dataset
data("iris")

# Produce a symmetric joint probability matrix
prob_matrix <- p2sp(x2p(as.matrix(iris[,1:4])))

# Estimate a mmtsne model with 2 maps, 2 dimensions each
model <- mmtsneP(prob_matrix, no_maps=2, max_iter=100)

# Plot the results side-by-side for inspection
# Points scaled by map proportion weights plus constant factor
par(mfrow=c(1,2))
plot(model$Y[,,1], col=iris$Species, cex=model$proportions[,1] + 0.2)
plot(model$Y[,,2], col=iris$Species, cex=model$proportions[,2] + 0.2)
par(mfrow=c(1,1))

# }