Multiplicative updates for t-SNE

It has been demonstrated that Student t-Distributed Stochastic Neighbor Embedding (t-SNE) can enhance discovery of clusters of data. However, the original t-SNE implementation employs an additive gradient-based algorithm which requires suitable learning step size and momentum rate, the tuning of which can be laborious. We propose a novel fixed-point algorithm that overcomes such parameter selection problems in t-SNE by using multiplicative updates in exponential space. Our algorithm is also the first application of the multiplicative update technique beyond nonnegative matrix factorization. Empirical results on two of three selected datasets indicate that the new method can produce even better visualizations than the original t-SNE algorithm.