English
Related papers

Related papers: Pulling back symmetric Riemannian geometry for dat…

200 papers

The integration of Symmetric Positive Definite (SPD) matrices into deep learning has historically relied on fixed algebraic Riemannian metrics. Analogous to hand-crafted features in classical machine learning, these static formulations…

Machine Learning · Computer Science 2026-05-07 Tushar Das , Subrata Dutta , Sarmistha Neogy , Koushlendra Kumar Singh

Riemannian geometry provides us with powerful tools to explore the latent space of generative models while preserving the underlying structure of the data. The latent space can be equipped it with a Riemannian metric, pulled back from the…

Machine Learning · Computer Science 2023-10-13 Alison Pouplin , David Eklund , Carl Henrik Ek , Søren Hauberg

Shape optimization is commonly applied in engineering to optimize shapes with respect to an objective functional relying on PDE solutions. In this paper, we view shape optimization as optimization on Riemannian shape manifolds. We consider…

Optimization and Control · Mathematics 2025-04-09 Estefania Loayza-Romero , Kathrin Welker

The real symplectic Stiefel manifold is the manifold of symplectic bases of symplectic subspaces of a fixed dimension. It features in a large variety of applications in physics and engineering. In this work, we study this manifold with the…

Differential Geometry · Mathematics 2021-08-31 Thomas Bendokat , Ralf Zimmermann

Deep Neural Networks are widely used for solving complex problems in several scientific areas, such as speech recognition, machine translation, image analysis. The strategies employed to investigate their theoretical properties mainly rely…

Machine Learning · Computer Science 2022-09-26 Alessandro Benfenati , Alessio Marta

The correlation matrix is a central representation of functional brain networks in neuroimaging. Traditional analyses often treat pairwise interactions independently in a Euclidean setting, overlooking the intrinsic geometry of correlation…

Machine Learning · Statistics 2025-04-10 Kisung You , Yelim Lee , Hae-Jeong Park

In this paper, I shall demonstrate that sufficiently high-dimensional closed positively-curved Riemannian manifolds are either diffeomorphic to a spherical space form, or isometric to a locally compact rank one symmetric space. This…

Metric Geometry · Mathematics 2016-08-05 Yashar Memarian

This paper advocates a novel framework for segmenting a dataset in a Riemannian manifold $M$ into clusters lying around low-dimensional submanifolds of $M$. Important examples of $M$, for which the proposed clustering algorithm is…

Machine Learning · Statistics 2014-10-02 Xu Wang , Konstantinos Slavakis , Gilad Lerman

Latent space geometry provides a rigorous and empirically valuable framework for interacting with the latent variables of deep generative models. This approach reinterprets Euclidean latent spaces as Riemannian through a pull-back metric,…

Machine Learning · Statistics 2024-08-15 Stas Syrota , Pablo Moreno-Muñoz , Søren Hauberg

This report concerns the problem of dimensionality reduction through information geometric methods on statistical manifolds. While there has been considerable work recently presented regarding dimensionality reduction for the purposes of…

Machine Learning · Statistics 2008-09-30 Kevin M. Carter , Raviv Raich , Alfred O. Hero

Symmetric positive definite (SPD) matrices arising from functional connectivity analysis of neuroimaging data can be endowed with a Riemannian geometric structure that standard methods fail to respect. While existing R packages provide some…

Computation · Statistics 2025-11-12 Nicolas Escobar-Velasquez

Meta-learning, or "learning to learn," aims to enable models to quickly adapt to new tasks with minimal data. While traditional methods like Model-Agnostic Meta-Learning (MAML) optimize parameters in Euclidean space, they often struggle to…

Machine Learning · Computer Science 2025-03-17 JuneYoung Park , YuMi Lee , Tae-Joon Kim , Jang-Hwan Choi

Real world data often lie on low-dimensional Riemannian manifolds embedded in high-dimensional spaces. This motivates learning degenerate normalizing flows that map between the ambient space and a low-dimensional latent space. However, if…

Machine Learning · Computer Science 2026-04-14 Hanlin Yu , Søren Hauberg , Marcelo Hartmann , Arto Klami , Georgios Arvanitidis

The space of embedded submanifolds plays an important role in applications such as computational anatomy and shape analysis. We can define two different classes on Riemannian metrics on this space: so-called outer metrics are metrics that…

Differential Geometry · Mathematics 2017-09-19 Martins Bruveris

In this paper, we develop a new classification method for manifold-valued data in the framework of probabilistic learning vector quantization. In many classification scenarios, the data can be naturally represented by symmetric positive…

Machine Learning · Computer Science 2021-02-02 Fengzhen Tang , Haifeng Feng , Peter Tino , Bailu Si , Daxiong Ji

When generalizing schemes for real-valued data approximation or decomposition to data living in Riemannian manifolds, tangent space-based schemes are very attractive for the simple reason that these spaces are linear. An open challenge is…

Numerical Analysis · Mathematics 2023-06-02 Willem Diepeveen , Joyce Chew , Deanna Needell

This paper proposes a general framework of Riemannian adaptive optimization methods. The framework encapsulates several stochastic optimization algorithms on Riemannian manifolds and incorporates the mini-batch strategy that is often used…

Optimization and Control · Mathematics 2025-02-14 Hiroyuki Sakai , Hideaki Iiduka

Given data, deep generative models, such as variational autoencoders (VAE) and generative adversarial networks (GAN), train a lower dimensional latent representation of the data space. The linear Euclidean geometry of data space pulls back…

Computer Vision and Pattern Recognition · Computer Science 2018-05-22 Line Kuhnel , Tom Fletcher , Sarang Joshi , Stefan Sommer

This paper advocates Riemannian multi-manifold modeling in the context of network-wide non-stationary time-series analysis. Time-series data, collected sequentially over time and across a network, yield features which are viewed as points…

We propose Pullback Flow Matching (PFM), a novel framework for generative modeling on data manifolds. Unlike existing methods that assume or learn restrictive closed-form manifold mappings for training Riemannian Flow Matching (RFM) models,…

Machine Learning · Computer Science 2025-07-10 Friso de Kruiff , Erik Bekkers , Ozan Öktem , Carola-Bibiane Schönlieb , Willem Diepeveen