Johnson-Lindenstrauss Lemma Beyond Euclidean Geometry

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Deng, Chengyuan, Gao, Jie, Lu, Kevin, Luo, Feng, Xin, Cheng
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866912670453596160
author Deng, Chengyuan
Gao, Jie
Lu, Kevin
Luo, Feng
Xin, Cheng
author_facet Deng, Chengyuan
Gao, Jie
Lu, Kevin
Luo, Feng
Xin, Cheng
contents The Johnson-Lindenstrauss (JL) lemma is a cornerstone of dimensionality reduction in Euclidean space, but its applicability to non-Euclidean data has remained limited. This paper extends the JL lemma beyond Euclidean geometry to handle general dissimilarity matrices that are prevalent in real-world applications. We present two complementary approaches: First, we show the JL transform can be applied to vectors in pseudo-Euclidean space with signature $(p,q)$, providing theoretical guarantees that depend on the ratio of the $(p, q)$ norm and Euclidean norm of two vectors, measuring the deviation from Euclidean geometry. Second, we prove that any symmetric hollow dissimilarity matrix can be represented as a matrix of generalized power distances, with an additional parameter representing the uncertainty level within the data. In this representation, applying the JL transform yields multiplicative approximation with a controlled additive error term proportional to the deviation from Euclidean geometry. Our theoretical results provide fine-grained performance analysis based on the degree to which the input data deviates from Euclidean geometry, making practical and meaningful reduction in dimensionality accessible to a wider class of data. We validate our approaches on both synthetic and real-world datasets, demonstrating the effectiveness of extending the JL lemma to non-Euclidean settings.
format Preprint
id arxiv_https___arxiv_org_abs_2510_22401
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Johnson-Lindenstrauss Lemma Beyond Euclidean Geometry
Deng, Chengyuan
Gao, Jie
Lu, Kevin
Luo, Feng
Xin, Cheng
Data Structures and Algorithms
The Johnson-Lindenstrauss (JL) lemma is a cornerstone of dimensionality reduction in Euclidean space, but its applicability to non-Euclidean data has remained limited. This paper extends the JL lemma beyond Euclidean geometry to handle general dissimilarity matrices that are prevalent in real-world applications. We present two complementary approaches: First, we show the JL transform can be applied to vectors in pseudo-Euclidean space with signature $(p,q)$, providing theoretical guarantees that depend on the ratio of the $(p, q)$ norm and Euclidean norm of two vectors, measuring the deviation from Euclidean geometry. Second, we prove that any symmetric hollow dissimilarity matrix can be represented as a matrix of generalized power distances, with an additional parameter representing the uncertainty level within the data. In this representation, applying the JL transform yields multiplicative approximation with a controlled additive error term proportional to the deviation from Euclidean geometry. Our theoretical results provide fine-grained performance analysis based on the degree to which the input data deviates from Euclidean geometry, making practical and meaningful reduction in dimensionality accessible to a wider class of data. We validate our approaches on both synthetic and real-world datasets, demonstrating the effectiveness of extending the JL lemma to non-Euclidean settings.
title Johnson-Lindenstrauss Lemma Beyond Euclidean Geometry
topic Data Structures and Algorithms
url https://arxiv.org/abs/2510.22401