English
Related papers

Related papers: Metrics for Probabilistic Geometries

200 papers

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

It can be difficult to tell whether a trained generative model has learned to generate novel examples or has simply memorized a specific set of outputs. In published work, it is common to attempt to address this visually, for example by…

Machine Learning · Computer Science 2017-05-29 Matt Feiszli

Modern generative models can produce realistic samples, however, balancing memorisation and generalisation remains an open problem. We approach this challenge from a Bayesian perspective by focusing on the parameter space of flow matching…

Data which lie in the space $\mathcal{P}_{m\,}$, of $m \times m$ symmetric positive definite matrices, (sometimes called tensor data), play a fundamental role in applications including medical imaging, computer vision, and radar signal…

Statistics Theory · Mathematics 2016-12-09 Salem Said , Lionel Bombrun , Yannick Berthoumieu , Jonathan Manton

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

The Riemannian geometry of covariance matrices has been essential to several successful applications, in computer vision, biomedical signal and image processing, and radar data processing. For these applications, an important ongoing…

Statistics Theory · Mathematics 2017-05-15 Salem Said , Hatem Hajri , Lionel Bombrun , Baba C. Vemuri

We study the Wasserstein natural gradient in parametric statistical models with continuous sample spaces. Our approach is to pull back the $L^2$-Wasserstein metric tensor in the probability density space to a parameter space, equipping the…

Optimization and Control · Mathematics 2024-08-20 Yifan Chen , Wuchen Li

Stochastic generative models enable us to capture the geometric structure of a data manifold lying in a high dimensional space through a Riemannian metric in the latent space. However, its practical use is rather limited mainly due to…

Machine Learning · Statistics 2021-03-10 Georgios Arvanitidis , Bogdan Georgiev , Bernhard Schölkopf

Recently, Riemannian Gaussian distributions were defined on spaces of positive-definite real and complex matrices. The present paper extends this definition to the space of positive-definite quaternion matrices. In order to do so, it…

Statistics Theory · Mathematics 2017-03-30 Salem Said , Nicolas Le Bihan , Jonathan H. Manton

Deep generative models like variational autoencoders approximate the intrinsic geometry of high dimensional data manifolds by learning low-dimensional latent-space variables and an embedding function. The geometric properties of these…

Computer Vision and Pattern Recognition · Computer Science 2019-02-20 Ankita Shukla , Shagun Uppal , Sarthak Bhagat , Saket Anand , Pavan Turaga

Random geometric graphs are random graph models defined on metric spaces. Such a model is defined by first sampling points from a metric space and then connecting each pair of sampled points with probability that depends on their distance,…

Machine Learning · Computer Science 2026-04-10 Han Huang , Pakawut Jiradilok , Elchanan Mossel

Great computational effort is invested in generating equilibrium states for molecular systems using, for example, Markov chain Monte Carlo. We present a probabilistic model that generates statistically independent samples for molecules from…

Machine Learning · Statistics 2021-02-09 Gregor N. C. Simm , José Miguel Hernández-Lobato

Latent space geometry has shown itself to provide a rich and rigorous framework for interacting with the latent variables of deep generative models. The existing theory, however, relies on the decoder being a Gaussian distribution as its…

Machine Learning · Computer Science 2022-04-26 Georgios Arvanitidis , Miguel González-Duque , Alison Pouplin , Dimitris Kalatzis , Søren Hauberg

We present a probabilistic model where the latent variable respects both the distances and the topology of the modeled data. The model leverages the Riemannian geometry of the generated manifold to endow the latent space with a well-defined…

Machine Learning · Statistics 2021-06-09 Martin Jørgensen , Søren Hauberg

Gaussian Process (GP) regression is a powerful nonparametric Bayesian framework, but its performance depends critically on the choice of covariance kernel. Selecting an appropriate kernel is therefore central to model quality, yet remains…

Machine Learning · Computer Science 2026-01-14 Md Shafiqul Islam , Shakti Prasad Padhy , Douglas Allaire , Raymundo Arróyave

Random geometric graphs are random graph models defined on metric measure spaces. A random geometric graph is generated by first sampling points from a metric space and then connecting each pair of sampled points independently with a…

Probability · Mathematics 2025-11-10 Han Huang , Pakawut Jiradilok , Elchanan Mossel

Graph diffusion models have made significant progress in learning structured graph data and have demonstrated strong potential for predictive tasks. Existing approaches typically embed node, edge, and graph-level features into a unified…

Machine Learning · Computer Science 2025-12-12 Yisen Gao , Xingcheng Fu , Qingyun Sun , Jianxin Li , Xianxian Li

Generalized tensor analysis in the sense of Colombeau's construction is employed to introduce a nonlinear distributional pseudo-Riemannian geometry. In particular, after deriving several characterizations of invertibility in the algebra of…

Functional Analysis · Mathematics 2007-05-23 Michael Kunzinger , Roland Steinbauer

We propose a manifold matching approach to generative models which includes a distribution generator (or data generator) and a metric generator. In our framework, we view the real data set as some manifold embedded in a high-dimensional…

Computer Vision and Pattern Recognition · Computer Science 2021-08-30 Mengyu Dai , Haibin Hang

This paper introduces a new interpretation of the Variational Autoencoder framework by taking a fully geometric point of view. We argue that vanilla VAE models unveil naturally a Riemannian structure in their latent space and that taking…

Machine Learning · Statistics 2022-11-04 Clément Chadebec , Stéphanie Allassonnière