English

Convergence analysis of t-SNE as a gradient flow for point cloud on a manifold

Machine Learning 2024-02-01 v1 Data Structures and Algorithms Machine Learning

Abstract

We present a theoretical foundation regarding the boundedness of the t-SNE algorithm. t-SNE employs gradient descent iteration with Kullback-Leibler (KL) divergence as the objective function, aiming to identify a set of points that closely resemble the original data points in a high-dimensional space, minimizing KL divergence. Investigating t-SNE properties such as perplexity and affinity under a weak convergence assumption on the sampled dataset, we examine the behavior of points generated by t-SNE under continuous gradient flow. Demonstrating that points generated by t-SNE remain bounded, we leverage this insight to establish the existence of a minimizer for KL divergence.

Keywords

Cite

@article{arxiv.2401.17675,
  title  = {Convergence analysis of t-SNE as a gradient flow for point cloud on a manifold},
  author = {Seonghyeon Jeong and Hau-Tieng Wu},
  journal= {arXiv preprint arXiv:2401.17675},
  year   = {2024}
}