How do I calculate a similarity matrix with a Student-t kernel?

Question

As the title says, how do I calculate a similarity matrix with an un-normalized Student-t kernel? I’m attempting to calculate Kullback-Leibler divergence for different t-SNE runs, but need a Q-matrix for that. A few steps before the Q-matrix, I need the similarity matrices made using the un-normalized Student-t kernel.

I’m using r, not sure if that’s relevant to an answer.

dataset r similarity tsne visualization

I'm using r, not sure if that's relevant to an answer.

Pieter · Answer

You can use dt from the stats to get the density of a Student-t distribution. See the help page for extra information about this, and related, functions.

An example, showing the Student-t distrib

library(stats)

xs = seq(-5, 5, .1)
density = dt(xs, df=1)

plot(xs, density)

How do I calculate a similarity matrix with a Student-t kernel?

One Answer

Add your own answers!

Ask a Question