Salvato in:
Dettagli Bibliografici
Autori principali: Jeong, Seonghyeon, Wu, Hau-Tieng
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:https://arxiv.org/abs/2401.17675
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866929230182350848
author Jeong, Seonghyeon
Wu, Hau-Tieng
author_facet Jeong, Seonghyeon
Wu, Hau-Tieng
contents We present a theoretical foundation regarding the boundedness of the t-SNE algorithm. t-SNE employs gradient descent iteration with Kullback-Leibler (KL) divergence as the objective function, aiming to identify a set of points that closely resemble the original data points in a high-dimensional space, minimizing KL divergence. Investigating t-SNE properties such as perplexity and affinity under a weak convergence assumption on the sampled dataset, we examine the behavior of points generated by t-SNE under continuous gradient flow. Demonstrating that points generated by t-SNE remain bounded, we leverage this insight to establish the existence of a minimizer for KL divergence.
format Preprint
id arxiv_https___arxiv_org_abs_2401_17675
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Convergence analysis of t-SNE as a gradient flow for point cloud on a manifold
Jeong, Seonghyeon
Wu, Hau-Tieng
Machine Learning
Data Structures and Algorithms
90C26, 90C30
F.2.2; F.2.0; G.4
We present a theoretical foundation regarding the boundedness of the t-SNE algorithm. t-SNE employs gradient descent iteration with Kullback-Leibler (KL) divergence as the objective function, aiming to identify a set of points that closely resemble the original data points in a high-dimensional space, minimizing KL divergence. Investigating t-SNE properties such as perplexity and affinity under a weak convergence assumption on the sampled dataset, we examine the behavior of points generated by t-SNE under continuous gradient flow. Demonstrating that points generated by t-SNE remain bounded, we leverage this insight to establish the existence of a minimizer for KL divergence.
title Convergence analysis of t-SNE as a gradient flow for point cloud on a manifold
topic Machine Learning
Data Structures and Algorithms
90C26, 90C30
F.2.2; F.2.0; G.4
url https://arxiv.org/abs/2401.17675