Metric-Aware PCA as a Linear Instance of Geometric Deep Learning

• URL: http://arxiv.org/abs/2605.27456v1
• Date: Mon, 25 May 2026 16:07:24 GMT
• Title: Metric-Aware PCA as a Linear Instance of Geometric Deep Learning
• Abstract summary: Metric-Aware Principal Component Analysis (MAPCA) parameterises principal component analysis by a positive-definite metric matrix.<n>This paper positions MAPCA within the geometric deep learning framework.<n>We construct a precise dictionary between MAPCA and geometric deep learning.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Geometric deep learning organises neural architectures around the symmetries of their data domain, with the choice of symmetry group serving as a geometric prior that determines what representations can be learned. Metric-Aware Principal Component Analysis (MAPCA) parameterises principal component analysis by a positive-definite metric matrix, with a canonical subfamily interpolating between standard PCA and output whitening and a diagonal-metric point recovering Invariant PCA (IPCA). This paper positions MAPCA within the geometric deep learning framework. The metric is read as the geometric prior; the orthogonal group preserving it is the symmetry group it induces; MAPCA solutions are equivariant under this group with the resulting spectrum invariant; and MAPCA's defining constraint is the linear analogue of the Schur-type weight constraints used in equivariant networks. Across six axes - domain, symmetry group, equivariance, invariance, architectural primitive, and geometric prior - we construct a precise dictionary between MAPCA and geometric deep learning. The technical anchor is a uniqueness theorem characterising IPCA as the unique linear data-derived metric in the MAPCA family that is equivariant under arbitrary diagonal rescaling and projects onto the fixed-point set of the action, equivalent under normalisation to the variance-maximisation criterion in its precise form. The paper closes with three bridges: kernel PCA as the nonlinear extension, spectral graph methods as MAPCA on graphs, and a deep MAPCA construction extending the positioning into deep equivariant networks

Related papers

• Shape Operator PCA: Curvature-Aware Projections for Geometric Machine Learning [52.452902154360565]
  SHOPCA (Shape Operator-based Principal Component Analysis) is a novel method for unsupervised metric learning and dimensionality reduction.<n>We evaluate SHOPCA on more than 50 real-world benchmark datasets.
  arXiv  Detail & Related papers  (2026-08-15T16:37:47Z)
• A Geometric Measure of Linear Separability for Neural Representations [12.476368894025233]
  We introduce the directional linear separability measure (LSM), a finite-sample diagnostic for one-sided affine separability.<n>For a target class A and a competing set B, LSM measures the smallest competing-sample intrusion that must remain on the target side, normalized by |A|.
  arXiv  Detail & Related papers  (2026-06-07T16:31:54Z)
• Beyond Rigid Geometries: The Spline-Pullback Metric for Universal Diffeomorphic SPD Representation Learning [2.704566511657017]
  In this paper, we introduce the Spline-Pullback Metric (SPM), instantiated as Spectral-SPM and Cholesky-SPM.<n>By parameterizing the global diffeomorphism via a rank-invariant, B-spline, SPM acts as a dense universal approximator for strictly increasing $C1$ diffeomorphisms.<n>SPM achieves a state-of-the-art performance across 3 datasets utilizing Linear Probes, SPDNets, and deep Riemannian ResNets.
  arXiv  Detail & Related papers  (2026-05-06T01:55:45Z)
• 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)
• Curvature-Aware PCA with Geodesic Tangent Space Aggregation for Semi-Supervised Learning [52.452902154360565]
  GTSA-PCA is a geometric extension of Principal Component Analysis.<n>It integrates curvature awareness and geodesic consistency within a unified spectral framework.<n>Our results position GTSA-PCA as a principled bridge between statistical and geometric approaches to dimensionality reduction.
  arXiv  Detail & Related papers  (2026-04-20T20:36:36Z)
• Geometric structures and deviations on James' symmetric positive-definite matrix bicone domain [7.183268823159973]
  We introduce two new structures, a Finslerian structure and a dual information-geometric structure.<n>These structures ensure that geodesics correspond to straight lines in appropriate coordinate systems.<n>We discuss several applications of these Finsler/dual Hessian structures and provide various inequalities between the new and traditional dissimilarities.
  arXiv  Detail & Related papers  (2026-03-03T00:10:32Z)
• CAT: Curvature-Adaptive Transformers for Geometry-Aware Learning [0.0]
  Curvature-Adaptive Transformer (CAT) learns per-token routing across three geometric attention branches through a lightweight, differentiable gating mechanism.<n>On knowledge graph completion benchmarks, CAT achieves approximately 10% improvements in MRR and Hits@10 over fixed-geometry baselines with minimal overhead.
  arXiv  Detail & Related papers  (2025-10-02T03:26:33Z)
• 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)
• PAID: Pairwise Angular-Invariant Decomposition for Continual Test-Time Adaptation [70.98107766265636]
  This paper takes the geometric attributes of pre-trained weights as a starting point, systematically analyzing three key components: magnitude, absolute angle, and pairwise angular structure.<n>We find that the pairwise angular structure remains stable across diverse corrupted domains and encodes domain-invariant semantic information, suggesting it should be preserved during adaptation.
  arXiv  Detail & Related papers  (2025-06-03T05:18:15Z)
• Incorporating Arbitrary Matrix Group Equivariance into KANs [69.30866522377694]
  Kolmogorov-Arnold Networks (KANs) have seen great success in scientific domains.<n>We propose Equivariant Kolmogorov-Arnold Networks (EKAN) to broaden their applicability to more fields.
  arXiv  Detail & Related papers  (2024-10-01T06:34:58Z)
• Understanding Matrix Function Normalizations in Covariance Pooling through the Lens of Riemannian Geometry [63.694184882697435]
  Global Covariance Pooling (GCP) has been demonstrated to improve the performance of Deep Neural Networks (DNNs) by exploiting second-order statistics of high-level representations.<n>This paper provides a comprehensive and unified understanding of the matrix logarithm and power from a Riemannian geometry perspective.
  arXiv  Detail & Related papers  (2024-07-15T07:11:44Z)
• Differential geometry with extreme eigenvalues in the positive semidefinite cone [1.9116784879310025]
  We present a route to a scalable geometric framework for the analysis and processing of SPD-valued data based on the efficient of extreme generalized eigenvalues. We define a novel iterative mean of SPD matrices based on this geometry and prove its existence and uniqueness for a given finite collection of points.
  arXiv  Detail & Related papers  (2023-04-14T18:37:49Z)
• Improving Metric Dimensionality Reduction with Distributed Topology [68.8204255655161]
  DIPOLE is a dimensionality-reduction post-processing step that corrects an initial embedding by minimizing a loss functional with both a local, metric term and a global, topological term. We observe that DIPOLE outperforms popular methods like UMAP, t-SNE, and Isomap on a number of popular datasets.
  arXiv  Detail & Related papers  (2021-06-14T17:19:44Z)

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.