t-SNE, Forceful Colorings and Mean Field Limits
Yulan Zhang, Stefan Steinerberger

TL;DR
This paper introduces forceful colorings for force-based dimensionality reduction methods and analyzes the mean-field limit of t-SNE on a homogeneous cluster, revealing a novel annular embedding structure.
Contribution
It presents the concept of forceful colorings applicable to various force-based methods and derives a mean-field model predicting the t-SNE embedding shape for homogeneous clusters.
Findings
Forceful colorings provide additional features from force vectors.
t-SNE on a homogeneous cluster forms a thin annulus in the limit.
Numerical results support the mean-field predictions.
Abstract
t-SNE is one of the most commonly used force-based nonlinear dimensionality reduction methods. This paper has two contributions: the first is forceful colorings, an idea that is also applicable to other force-based methods (UMAP, ForceAtlas2,...). In every equilibrium, the attractive and repulsive forces acting on a particle cancel out: however, both the size and the direction of the attractive (or repulsive) forces acting on a particle are related to its properties: the force vector can serve as an additional feature. Secondly, we analyze the case of t-SNE acting on a single homogeneous cluster (modeled by affinities coming from the adjacency matrix of a random k-regular graph); we derive a mean-field model that leads to interesting questions in classical calculus of variations. The model predicts that, in the limit, the t-SNE embedding of a single perfectly homogeneous cluster is not…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsGenomics and Chromatin Dynamics · Machine Learning in Materials Science
