The Data Manifold under the Microscope

• URL: http://arxiv.org/abs/2606.15760v1
• Date: Sun, 14 Jun 2026 11:45:58 GMT
• Title: The Data Manifold under the Microscope
• Abstract summary: Generalization and approximation error bounds are often derived for simplified models or are too loose to be informative.<n>We introduce a benchmarking framework for studying data geometry.<n>The framework is intended as a controlled testbed, useful as a calibration environment for geometric estimators.
• Score: 3.9636286063751895
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: A significant gap exists between theory and practice in deep learning. Generalization and approximation error bounds are often derived for simplified models or are too loose to be informative. Many rely on the manifold hypothesis and on geometric regularity such as intrinsic dimension, curvature, and reach. Progress requires insight into data-manifold geometry and suitable benchmarks, yet existing options are polarized: analytic manifolds with known geometry but limited applicability, or real-world datasets where geometry is only coarsely estimable. We introduce a benchmarking framework for studying data geometry. We repurpose and extend dSprites and COIL-20 with additional transformation dimensions and dense, axis-aligned sampling, and pair them with finite-difference estimators that recover curvature, reach, and volume at near-ground-truth accuracy in a regime where general-purpose estimators are unreliable or difficult to deploy. The framework is intended as a controlled testbed, useful as a calibration environment for geometric estimators and a sandbox for probing theoretical assumptions. To illustrate its use, we present two application studies, namely assessing the scaling behavior of the bounds of Genovese et al. and Fefferman et al., and tracking the layer-wise geometry of a $β$-VAE, highlighting the behavior of current bounds and the value of controlled benchmarks for guiding and validating future theory. A reference implementation is available at https://github.com/koulakis/manifold-microscope.

Related papers

• Riemannian Metric Matching for Scalable Geometric Modeling of Distributions [3.858534299063136]
  We propose a denoising probabilistic framework for learning the Riemannian geometry of data using neural networks.<n>Specifically, we learn the carré du champ operator, which, using diffusion geometry, gives us access to the Riemannian geometry toolkit for downstream machine learning and statistical tasks.<n> Empirically, metric matching rivals or improves the accuracy of $k$-NN-based diffusion geometry estimators, while enabling amortized inference that is up to $400times$ faster.
  arXiv  Detail & Related papers  (2026-06-12T10:41:44Z)
• Learning Point Cloud Geometry as a Statistical Manifold: Theory and Practice [11.695017334165287]
  LiDAR-acquired point clouds are inherently sparse and non-uniform.<n>Existing approaches attempt to compensate for these limitations by estimating local geometry.<n>We introduce Point-to-Ellipsoid (POLI), a deep neural estimator that predicts per-point Gaussian geometry.
  arXiv  Detail & Related papers  (2026-05-11T12:27:25Z)
• A Mean Curvature Approach to Boundary Detection: Geometric Insights for Unsupervised Learning [52.452902154360565]
  We introduce Mean Curvature Boundary Points (MCBP), a novel geometric framework grounded in Geometric Machine Learning.<n>MCBP explicitly models the intrinsic curvature of the data manifold and computes pointwise mean curvature without requiring principled manifold parametrization.<n>Experiments on synthetic and real-world datasets demonstrate that MCBP consistently improves clustering performance.
  arXiv  Detail & Related papers  (2026-05-05T20:19:09Z)
• GeoDM: Geometry-aware Distribution Matching for Dataset Distillation [5.993128231927707]
  We propose a geometry-aware distribution-matching framework, called textbfGeoDM.<n>To adapt to the underlying data geometry, we introduce learnable curvature and weight parameters for three kinds of geometries.<n>Our theoretical analysis shows that the geometry-aware distribution matching in a product space yields a smaller generalization error bound than the Euclidean counterparts.
  arXiv  Detail & Related papers  (2025-12-09T07:31:57Z)
• Variational Geometric Information Bottleneck: Learning the Shape of Understanding [0.0]
  Variational Geometric Information Bottleneck (V-GIB) is a variational estimator that unifies mutual-information compression and curvature regularization.<n>V-GIB provides a principled and measurable route to representations that are geometrically coherent, data-efficient, and aligned with human-understandable structure.
  arXiv  Detail & Related papers  (2025-11-04T11:33:54Z)
• CP$^2$: Leveraging Geometry for Conformal Prediction via Canonicalization [51.716834831684004]
  We study the problem of conformal prediction (CP) under geometric data shifts.<n>We propose integrating geometric information--such as geometric pose--into the conformal procedure to reinstate its guarantees.
  arXiv  Detail & Related papers  (2025-06-19T10:12:02Z)
• Follow the Energy, Find the Path: Riemannian Metrics from Energy-Based Models [63.331590876872944]
  We propose a method for deriving Riemannian metrics directly from pretrained Energy-Based Models.<n>These metrics define spatially varying distances, enabling the computation of geodesics.<n>We show that EBM-derived metrics consistently outperform established baselines.
  arXiv  Detail & Related papers  (2025-05-23T12:18:08Z)
• Bridging Geometric States via Geometric Diffusion Bridge [79.60212414973002]
  We introduce the Geometric Diffusion Bridge (GDB), a novel generative modeling framework that accurately bridges initial and target geometric states. GDB employs an equivariant diffusion bridge derived by a modified version of Doob's $h$-transform for connecting geometric states. We show that GDB surpasses existing state-of-the-art approaches, opening up a new pathway for accurately bridging geometric states.
  arXiv  Detail & Related papers  (2024-10-31T17:59:53Z)
• Score-based Pullback Riemannian Geometry: Extracting the Data Manifold Geometry using Anisotropic Flows [10.649159213723106]
  We propose a framework for data-driven Riemannian geometry that is scalable in both geometry and learning.<n>We show that the proposed framework produces high-quality geodesics passing through the data support.<n>This is the first scalable framework for extracting the complete geometry of the data manifold.
  arXiv  Detail & Related papers  (2024-10-02T18:52:12Z)
• Disentangled Representation Learning with the Gromov-Monge Gap [65.73194652234848]
  Learning disentangled representations from unlabelled data is a fundamental challenge in machine learning.<n>We introduce a novel approach to disentangled representation learning based on quadratic optimal transport.<n>We demonstrate the effectiveness of our approach for quantifying disentanglement across four standard benchmarks.
  arXiv  Detail & Related papers  (2024-07-10T16:51:32Z)
• GELATO: Geometrically Enriched Latent Model for Offline Reinforcement Learning [54.291331971813364]
  offline reinforcement learning approaches can be divided into proximal and uncertainty-aware methods. In this work, we demonstrate the benefit of combining the two in a latent variational model. Our proposed metrics measure both the quality of out of distribution samples as well as the discrepancy of examples in the data.
  arXiv  Detail & Related papers  (2021-02-22T19:42:40Z)
• Identifying the latent space geometry of network models through analysis of curvature [7.644165047073435]
  We present a method to consistently estimate the manifold type, dimension, and curvature from an empirically relevant class of latent spaces. Our core insight comes by representing the graph as a noisy distance matrix based on the ties between cliques.
  arXiv  Detail & Related papers  (2020-12-19T00:35:29Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.