Some Theoretical Limitations of t-SNE

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Rupert, Mossel, Elchanan
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908964977901568
author Li, Rupert
Mossel, Elchanan
author_facet Li, Rupert
Mossel, Elchanan
contents t-SNE has gained popularity as a dimension reduction technique, especially for visualizing data. It is well-known that all dimension reduction techniques may lose important features of the data. We provide a mathematical framework for understanding this loss for t-SNE by establishing a number of results in different scenarios showing how important features of data are lost by using t-SNE.
format Preprint
id arxiv_https___arxiv_org_abs_2604_13295
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Some Theoretical Limitations of t-SNE
Li, Rupert
Mossel, Elchanan
Machine Learning
Probability
t-SNE has gained popularity as a dimension reduction technique, especially for visualizing data. It is well-known that all dimension reduction techniques may lose important features of the data. We provide a mathematical framework for understanding this loss for t-SNE by establishing a number of results in different scenarios showing how important features of data are lost by using t-SNE.
title Some Theoretical Limitations of t-SNE
topic Machine Learning
Probability
url https://arxiv.org/abs/2604.13295