aiqbench analysis
HomID introduces a rigorous benchmarking suite using homogeneous manifolds with anisotropic embeddings to expose systematic failures in intrinsic dimension estimators that thrive only on standard isotropic data. By demonstrating how anisotropic distortions shift underlying distributions, this work provides critical insights into the robustness and theoretical limits of current machine learning dimensionality reduction techniques.
HomID : Benchmarking Intrinsic Dimension Estimators on Homogenous Manifolds with Anisotropic Embeddings
arXiv:2510.01335v2 Announce Type: replace Abstract: The manifold hypothesis suggests that data lies on manifolds with smaller intrinsic dimension (ID) than their ambient dimension. However there is no empirical agreement on the estimates for ID from different estimators for realistic datasets. Thus it is important to test ID estimators (IDEs) with targeted stressors. In this work, we consider the role of anisotropy. To this end, we propose HomID, a collection of homogeneous spaces with anisotropic embedding, for benchmarking ID estimators. We observe that methods that perform well on standard benchmarks systematically degrade on HomID under identical resource allocation. We further observe that anisotropic distortion of such benchmarks also results in performance degradation. Finally, we demonstrate that controlled anisotropic distortions induce systematic shifts in the distributions on which these methods rely, providing a concrete mechanism for the resulting estimation errors in two particular IDEs.
Abstract:The manifold hypothesis suggests that data lies on manifolds with smaller intrinsic dimension (ID) than their ambient dimension. However there is no empirical agreement on the estimates for ID from different estimators for realistic datasets. Thus it is important to test ID estimators (IDEs) with targeted stressors. In this work, we consider the role of anisotropy. To this end, we propose HomID, a collection of homogeneous spaces with anisotropic embedding, for benchmarking ID estimators. We observe that methods that perform well on standard benchmarks systematically degrade on HomID under identical resource allocation. We further observe that anisotropic distortion of such benchmarks also results in performance degradation. Finally, we demonstrate that controlled anisotropic distortions induce systematic shifts in the distributions on which these methods rely, providing a concrete mechanism for the resulting estimation errors in two particular IDEs.
Machine Learning (cs.LG); Disordered Systems and Neural Networks (cond-mat.dis-nn); Metric Geometry (math.MG); Data Analysis, Statistics and Probability (physics.data-an); Quantum Physics (quant-ph)
arXiv:2510.01335 [cs.LG]
(or arXiv:2510.01335v2 [cs.LG] for this version)
Full text under the publisher's open licence · 166 words
Related coverage
The Data Manifold under the Microscope
arXiv · Jun 16, 2026
Interpretable intrinsic dimension estimation through componentwise calibration of distance and angle
arXiv · Sep 30, 2026
PersonaManifold: Revealing and Exploiting Curved Geometry in LLM Persona Representations
arXiv · Sep 29, 2026
Heat Field Signatures: From Point Clouds to Smooth Geometry
arXiv · Sep 9, 2026