Iso-Riemannian Optimization on Learned Data Manifolds

• URL: http://arxiv.org/abs/2510.21033v1
• Date: Thu, 23 Oct 2025 22:34:55 GMT
• Title: Iso-Riemannian Optimization on Learned Data Manifolds
• Authors: Willem Diepeveen, Melanie Weber,
• Abstract summary: We introduce a principled framework for optimization on learned data manifold using iso-Riemannian geometry.<n>We show that our approach yields interpretable barycentres, improved clustering, and provably efficient solutions to inverse problems.<n>These results establish that optimization under iso-Riemannian geometry can overcome distortions inherent to learned manifold mappings.
• Score: 6.345340156849189
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: High-dimensional data that exhibit an intrinsic low-dimensional structure are ubiquitous in machine learning and data science. While various approaches allow for learning the corresponding data manifold from finite samples, performing downstream tasks such as optimization directly on these learned manifolds presents a significant challenge. This work introduces a principled framework for optimization on learned data manifolds using iso-Riemannian geometry. Our approach addresses key limitations of classical Riemannian optimization in this setting, specifically, that the Levi-Civita connection fails to yield constant-speed geodesics, and that geodesic convexity assumptions break down under the learned pullback constructions commonly used in practice. To overcome these challenges, we propose new notions of monotonicity and Lipschitz continuity tailored to the iso-Riemannian setting and propose iso-Riemannian descent algorithms for which we provide a detailed convergence analysis. We demonstrate the practical effectiveness of those algorithms on both synthetic and real datasets, including MNIST under a learned pullback structure. Our approach yields interpretable barycentres, improved clustering, and provably efficient solutions to inverse problems, even in high-dimensional settings. These results establish that optimization under iso-Riemannian geometry can overcome distortions inherent to learned manifold mappings.

Related papers

• Dimensionality Reduction on Riemannian Manifolds in Data Analysis [0.0]
  Experimental results show improved representation quality and classification performance compared to Euclidean counterparts.<n>This study underscores the importance of geometry aware dimensionality reduction in modern machine learning and data science applications.
  arXiv  Detail & Related papers  (2026-02-05T17:46:58Z)
• Landing with the Score: Riemannian Optimization through Denoising [28.573407652000437]
  We introduce a link function that connects the data distribution to geometric operations needed for optimization.<n>We show that this function enables the recovery of essential manifold operations.<n>We propose two efficient inference-time algorithms.
  arXiv  Detail & Related papers  (2025-09-27T15:10:54Z)
• 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)
• Nonconvex Federated Learning on Compact Smooth Submanifolds With Heterogeneous Data [23.661713049508375]
  We propose an algorithm that learns over a submanifold in the setting of a client. We show that our proposed algorithm converges sub-ly to a neighborhood of a first-order optimal solution by using a novel analysis.
  arXiv  Detail & Related papers  (2024-06-12T17:53:28Z)
• FORML: A Riemannian Hessian-free Method for Meta-learning on Stiefel Manifolds [4.757859522106933]
  This paper introduces a Hessian-free approach that uses a first-order approximation of derivatives on the Stiefel manifold. Our method significantly reduces the computational load and memory footprint.
  arXiv  Detail & Related papers  (2024-02-28T10:57:30Z)
• Distributional Reduction: Unifying Dimensionality Reduction and Clustering with Gromov-Wasserstein [56.62376364594194]
  Unsupervised learning aims to capture the underlying structure of potentially large and high-dimensional datasets.<n>In this work, we revisit these approaches under the lens of optimal transport and exhibit relationships with the Gromov-Wasserstein problem.<n>This unveils a new general framework, called distributional reduction, that recovers DR and clustering as special cases and allows addressing them jointly within a single optimization problem.
  arXiv  Detail & Related papers  (2024-02-03T19:00:19Z)
• Stable Nonconvex-Nonconcave Training via Linear Interpolation [51.668052890249726]
  This paper presents a theoretical analysis of linearahead as a principled method for stabilizing (large-scale) neural network training. We argue that instabilities in the optimization process are often caused by the nonmonotonicity of the loss landscape and show how linear can help by leveraging the theory of nonexpansive operators.
  arXiv  Detail & Related papers  (2023-10-20T12:45:12Z)
• Linearization Algorithms for Fully Composite Optimization [61.20539085730636]
  This paper studies first-order algorithms for solving fully composite optimization problems convex compact sets. We leverage the structure of the objective by handling differentiable and non-differentiable separately, linearizing only the smooth parts.
  arXiv  Detail & Related papers  (2023-02-24T18:41:48Z)
• On a class of geodesically convex optimization problems solved via Euclidean MM methods [50.428784381385164]
  We show how a difference of Euclidean convexization functions can be written as a difference of different types of problems in statistics and machine learning. Ultimately, we helps the broader broader the broader the broader the broader the work.
  arXiv  Detail & Related papers  (2022-06-22T23:57:40Z)
• The Dynamics of Riemannian Robbins-Monro Algorithms [101.29301565229265]
  We propose a family of Riemannian algorithms generalizing and extending the seminal approximation framework of Robbins and Monro. Compared to their Euclidean counterparts, Riemannian algorithms are much less understood due to lack of a global linear structure on the manifold. We provide a general template of almost sure convergence results that mirrors and extends the existing theory for Euclidean Robbins-Monro schemes.
  arXiv  Detail & Related papers  (2022-06-14T12:30:11Z)
• First-Order Algorithms for Min-Max Optimization in Geodesic Metric Spaces [93.35384756718868]
  min-max algorithms have been analyzed in the Euclidean setting. We prove that the extraiteient (RCEG) method corrected lastrate convergence at a linear rate.
  arXiv  Detail & Related papers  (2022-06-04T18:53:44Z)
• Inferring Manifolds From Noisy Data Using Gaussian Processes [17.166283428199634]
  Most existing manifold learning algorithms replace the original data with lower dimensional coordinates. This article proposes a new methodology for addressing these problems, allowing the estimated manifold between fitted data points.
  arXiv  Detail & Related papers  (2021-10-14T15:50:38Z)
• Optimization on manifolds: A symplectic approach [127.54402681305629]
  We propose a dissipative extension of Dirac's theory of constrained Hamiltonian systems as a general framework for solving optimization problems. Our class of (accelerated) algorithms are not only simple and efficient but also applicable to a broad range of contexts.
  arXiv  Detail & Related papers  (2021-07-23T13:43:34Z)

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.