Equilibrium Distribution for t-Distributed Stochastic Neighbor Embedding with Generalized Kernels
This provides theoretical guarantees for t-SNE variants, which is incremental but important for practitioners using kernel modifications.
The paper proves that t-SNE with generalized kernels converges to an equilibrium distribution as data points increase, extending prior theoretical results.
T-distributed stochastic neighbor embedding (t-SNE) is a well-known algorithm for visualizing high-dimensional data by finding low-dimensional representations. In this paper, we study the convergence of t-SNE with generalized kernels and extend the results of Auffinger and Fletcher in 2023. Our work starts by giving a concrete formulation of generalized input and output kernels. Then we prove that under certain conditions, the t-SNE algorithm converges to an equilibrium distribution for a wide range of input and output kernels as the number of data points diverges.