Recovering the Euclidean Geometry of High-Dimensional Data Under Heterogeneous Noise

recovering-the-euclidean-geometry-of-high-dimensional-data-under-heterogeneous-noise

Recovering the Euclidean Geometry of High-Dimensional Data Under Heterogeneous Noise

[Submitted on 24 Jul 2025 (v1), last revised 13 Nov 2026 (this version, v3)]

View PDF HTML (experimental)

Abstract:Pairwise Euclidean distances provide a simple geometric representation of high-dimensional data and underlie many data analysis methods, including clustering, visualization, and manifold learning. However, in real-world applications, these distances can be severely corrupted by heterogeneous noise, where different data points are subject to different, and potentially large, noise levels. Such noise distorts the distances inhomogeneously, leading to a misrepresentation of the underlying data geometry. In this work, we ask whether the underlying clean Euclidean geometry can nevertheless be recovered from the corrupted pairwise distances. We answer this question affirmatively, showing that, perhaps surprisingly, such recovery is possible across a broad class of high-dimensional settings with underlying low-dimensional geometry, even when the noise magnitudes vary substantially across observations. We develop a principled approach for recovering the clean pairwise distances, without prior knowledge of either the clean data structure or the noise distribution, and establish probabilistic recovery guarantees. In particular, the recovery error converges to zero at polynomial rates as the feature dimension and dataset size increase simultaneously. Experiments on synthetic datasets demonstrate accurate recovery of the Euclidean geometry in challenging regimes and improved robustness of downstream methods that rely on pairwise distances. When applied to real single-cell RNA sequencing data, our method reliably recovers local neighborhood structure, enabling accurate nearest-neighbor identification used in many downstream analyses.

Submission history

From: Keyi Li [view email]
[v1] Thu, 24 Jul 2025 15:45:23 UTC (2,228 KB)
[v2] Thu, 11 Sep 2025 14:50:14 UTC (2,228 KB)
[v3] Fri, 13 Nov 2026 17:13:09 UTC (6,210 KB)