Some theoretical limitations of t-SNE
Proceedings of the National Academy of Sciences · 10.11.2026 · 123 (45)
DOI: 10.1073/pnas.2613435123 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the National Academy of Sciences, online erschienen am 05.11.2026. Verfasst von Rupert Li und 1 weiteren Autor:innen. Beteiligte Einrichtung: Department of Mathematics, Stanford University, Stanford, CA 94305. Die Arbeit nennt 17 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: Hertz Foundation (HF), Paul and Daisy Soros Fellowships for New Americans (PD Soros Fellowships), National Science Foundation (NSF).
Abstract (Originalsprache)
t-distributed Stochastic Neighborhood Embedding (t-SNE) has gained popularity as a dimension reduction technique, especially for visualizing data. It is well-known that dimension reduction may lose important data features. We provide a mathematical framework for understanding this loss for t-SNE, establishing several quantitative results across different scenarios that demonstrate how important structural information is lost.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Mathematics, Stanford University, Stanford, CA 94305.
- Department of Mathematics, Massachusetts Institute of Technology, Cambridge, MA 02139.
ORCID-Profile: Rupert Li, Elchanan Mossel
Förderung
- Hertz Foundation (HF)
- Paul and Daisy Soros Fellowships for New Americans (PD Soros Fellowships)
- National Science Foundation (NSF)
- DOW | USN | Office of Naval Research (ONR)
- Simons Foundation (SF)
Zitieren
APA
Li, R., & Mossel, E. (2026). Some theoretical limitations of t-SNE. Proceedings of the National Academy of Sciences, 123(45). https://doi.org/10.1073/pnas.2613435123
Vancouver
Li R, Mossel E. Some theoretical limitations of t-SNE. Proceedings of the National Academy of Sciences. 2026;123(45). doi:10.1073/pnas.2613435123
BibTeX
@article{Li2026,
author = {Li, Rupert and Mossel, Elchanan},
title = {Some theoretical limitations of t-SNE},
journal = {Proceedings of the National Academy of Sciences},
year = {2026},
volume = {123},
number = {45},
doi = {10.1073/pnas.2613435123}
}
EUVIMED