A Large-Dimensional Analysis of Symmetric SNE - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

A Large-Dimensional Analysis of Symmetric SNE

Résumé

Stochastic Neighbour Embedding methods (SNE, t-SNE) aim at finding a faithful low-dimensional representation of a high-dimensional dataset. Despite their popularity, being solution to a non-convex optimization, the behavior of these tools is not well understood. This work provides first answers by leveraging a large dimensional statistics approach, where the number n and dimension p of the large-dimensional data are of the same magnitude. We derive and study the canonical equation verified by the critical points of this non-convex optimization problem. The study notably reveals that, in a simple setup, the achievable SNE solutions correspond to a subset of those critical points. In particular, when the clusters composing the dataset are balanced in size, these solutions are symmetrical and assume closed-form expressions. As a major conclusion, the analysis rigorously proves a long-standing heuristic statement on the "proper normalization" of the symmetric SNE: out of two natural normalization choices, only the claimed proper one leads to non-trivial solutions.
Fichier principal
Vignette du fichier
sejourne.pdf (970.09 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03369132 , version 1 (07-10-2021)

Identifiants

Citer

Charles Tsuyoshi Sejourne, Romain Couillet, Pierre Comon. A Large-Dimensional Analysis of Symmetric SNE. ICASSP 2021 - IEEE International Conference on Acoustics, Speech, and Signal Processing, Jun 2021, Toronto, Canada. pp.2970-2974, ⟨10.1109/ICASSP39728.2021.9413583⟩. ⟨hal-03369132⟩
57 Consultations
114 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More