A Review of t-SNE

Обзор метода t-SNE
Sangwon Jung, Tristan Dagobert, Jean‐Michel Morel, Gabriele Facciolo
2024-10-31

accelerated t-SNEdimensionality reductionhigh-dimensional data visualizationstochastic neighbor embeddingt-SNE
High dimensional data is difficult to visualize. T-Distributed Stochastic Neighbor Embedding (t-SNE) is a popular technique for dimensionality reduction enabling a planar visualization of a dataset preserving as much as possible its metric. This paper explores the theoretical background of t-SNE and its accelerated version. A comparison of the performance of t-SNE on various datasets with different dimensions is also performed.
1
The method aims to preserve as much of the dataset’s metric structure as possible during visualization.
2
The paper reviews the theoretical foundations of t-SNE and its accelerated variant.
3
The performance of t-SNE is compared across multiple datasets with varying dimensionalities.
4
t-SNE is presented as a dimensionality-reduction technique for visualizing high-dimensional datasets in a planar representation.

t-SNE dimensionality-reduction visualization of high-dimensional datasets

The theoretical foundations, acceleration, and performance across datasets of t-SNE

Publication Details
Publication Date
2024-10-31
Journal
Publisher
ISSN
Access Type
Author Information
Authors
Sangwon Jung
Tristan Dagobert
Jean‐Michel Morel
Gabriele Facciolo
Explore further
Open the scid.ai AI chat with a ready-made request: it will find papers on a similar topic and help build a literature review.
Find similar papers in the chat →
Make a presentation
100%