Bounds on the geodesic distances on the Stiefel manifold for a family of Riemannian metrics
- URL: http://arxiv.org/abs/2408.07072v1
- Date: Thu, 25 Jul 2024 08:27:03 GMT
- Title: Bounds on the geodesic distances on the Stiefel manifold for a family of Riemannian metrics
- Authors: Simon Mataigne, P. -A. Absil, Nina Miolane,
- Abstract summary: We give bounds on geodesic distances on the Stiefel manifold.
These bounds aim at improving the theoretical guarantees and performance of minimal geodesic algorithms.
- Score: 2.913033886371052
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: We give bounds on geodesic distances on the Stiefel manifold, derived from new geometric insights. The considered geodesic distances are induced by the one-parameter family of Riemannian metrics introduced by H\"uper et al. (2021), which contains the well-known Euclidean and canonical metrics. First, we give the best Lipschitz constants between the distances induced by any two members of the family of metrics. Then, we give a lower and an upper bound on the geodesic distance by the easily computable Frobenius distance. We give explicit families of pairs of matrices that depend on the parameter of the metric and the dimensions of the manifold, where the lower and the upper bound are attained. These bounds aim at improving the theoretical guarantees and performance of minimal geodesic computation algorithms by reducing the initial velocity search space. In addition, these findings contribute to advancing the understanding of geodesic distances on the Stiefel manifold and their applications.
Related papers
- Product Geometries on Cholesky Manifolds with Applications to SPD Manifolds [65.04845593770727]
We present two new metrics on the Symmetric Positive Definite (SPD) manifold via the Cholesky manifold.
Our metrics are easy to use, computationally efficient, and numerically stable.
arXiv Detail & Related papers (2024-07-02T18:46:13Z) - Intrinsic Bayesian Cramér-Rao Bound with an Application to Covariance Matrix Estimation [49.67011673289242]
This paper presents a new performance bound for estimation problems where the parameter to estimate lies in a smooth manifold.
It induces a geometry for the parameter manifold, as well as an intrinsic notion of the estimation error measure.
arXiv Detail & Related papers (2023-11-08T15:17:13Z) - Curvature-Independent Last-Iterate Convergence for Games on Riemannian
Manifolds [77.4346324549323]
We show that a step size agnostic to the curvature of the manifold achieves a curvature-independent and linear last-iterate convergence rate.
To the best of our knowledge, the possibility of curvature-independent rates and/or last-iterate convergence has not been considered before.
arXiv Detail & Related papers (2023-06-29T01:20:44Z) - Short and Straight: Geodesics on Differentiable Manifolds [6.85316573653194]
In this work, we first analyse existing methods for computing length-minimising geodesics.
Second, we propose a model-based parameterisation for distance fields and geodesic flows on continuous manifold.
Third, we develop a curvature-based training mechanism, sampling and scaling points in regions of the manifold exhibiting larger values of the Ricci scalar.
arXiv Detail & Related papers (2023-05-24T15:09:41Z) - Identifying latent distances with Finslerian geometry [6.0188611984807245]
Generative models cause the data space and the geodesics to be at best impractical, and at worst impossible to manipulate.
In this work, we propose another metric whose geodesics explicitly minimise the expected length of the pullback metric.
In high dimensions, we prove that both metrics converge to each other at a rate of $Oleft(frac1Dright)$.
arXiv Detail & Related papers (2022-12-20T05:57:27Z) - 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) - GraphWalks: Efficient Shape Agnostic Geodesic Shortest Path Estimation [93.60478281489243]
We propose a learnable network to approximate geodesic paths on 3D surfaces.
The proposed method provides efficient approximations of the shortest paths and geodesic distances estimations.
arXiv Detail & Related papers (2022-05-30T16:22:53Z) - A singular Riemannian geometry approach to Deep Neural Networks I.
Theoretical foundations [77.86290991564829]
Deep Neural Networks are widely used for solving complex problems in several scientific areas, such as speech recognition, machine translation, image analysis.
We study a particular sequence of maps between manifold, with the last manifold of the sequence equipped with a Riemannian metric.
We investigate the theoretical properties of the maps of such sequence, eventually we focus on the case of maps between implementing neural networks of practical interest.
arXiv Detail & Related papers (2021-12-17T11:43:30Z) - Averaging on the Bures-Wasserstein manifold: dimension-free convergence
of gradient descent [15.136397170510834]
We prove new geodesic convexity results which provide stronger control of the iterates, a free convergence.
Our techniques also enable the analysis of two related notions of averaging, the entropically-regularized barycenter and the geometric median.
arXiv Detail & Related papers (2021-06-16T01:05:19Z) - Closed-form geodesics and trust-region method to calculate Riemannian
logarithms on Stiefel and its quotient manifolds [0.0]
We provide two closed-form geodesic formulas for a family of metrics on Stiefel manifold, parameterized by two positive numbers.
We show the logarithm map and geodesic distance between two endpoints on the manifold could be computed by it minimizing this square distance by a it trust-region solver.
arXiv Detail & Related papers (2021-03-12T16:48:38Z) - On the Local Linear Rate of Consensus on the Stiefel Manifold [39.750623187256735]
We restrict the convergence of properties of the Stfelian gradient over the Stiefel problem (for an un connected problem)
The main challenges include (i) developing a technical for analysis, and (ii) to identify the conditions (e.g., suitable step-size and under which the always stays in the local region) under which the always stays in the local region.
arXiv Detail & Related papers (2021-01-22T21:52:38Z)
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.