Recent advances in directional statistics

A Pewsey, E García-Portugués - Test, 2021 - Springer
Mainstream statistical methodology is generally applicable to data observed in Euclidean
space. There are, however, numerous contexts of considerable scientific interest in which …

Riemannian score-based generative modelling

V De Bortoli, E Mathieu, M Hutchinson… - Advances in …, 2022 - proceedings.neurips.cc
Score-based generative models (SGMs) are a powerful class of generative models that
exhibit remarkable empirical performance. Score-based generative modelling (SGM) …

Geometric neural diffusion processes

E Mathieu, V Dutordoir, M Hutchinson… - Advances in …, 2024 - proceedings.neurips.cc
Denoising diffusion models have proven to be a flexible and effective paradigm for
generative modelling. Their recent extension to infinite dimensional Euclidean spaces has …

A fully differentiable framework for 2D/3D registration and the projective spatial transformers

C Gao, A Feng, X Liu, RH Taylor… - IEEE transactions on …, 2023 - ieeexplore.ieee.org
Image-based 2D/3D registration is a critical technique for fluoroscopic guided surgical
interventions. Conventional intensity-based 2D/3D registration approa-ches suffer from a …

Geomnet: A neural network based on riemannian geometries of spd matrix space and cholesky space for 3d skeleton-based interaction recognition

XS Nguyen - Proceedings of the IEEE/CVF International …, 2021 - openaccess.thecvf.com
In this paper, we propose a novel method for representation and classification of two-person
interactions from 3D skeleton sequences. The key idea of our approach is to use Gaussian …

O (n)-invariant Riemannian metrics on SPD matrices

Y Thanwerdas, X Pennec - Linear Algebra and its Applications, 2023 - Elsevier
Abstract Symmetric Positive Definite (SPD) matrices are ubiquitous in data analysis under
the form of covariance matrices or correlation matrices. Several O (n)-invariant Riemannian …

Hyperbolic deep learning in computer vision: A survey

P Mettes, M Ghadimi Atigh, M Keller-Ressel… - International Journal of …, 2024 - Springer
Deep representation learning is a ubiquitous part of modern computer vision. While
Euclidean space has been the de facto standard manifold for learning visual …

Accelerated gradient methods for geodesically convex optimization: Tractable algorithms and convergence analysis

J Kim, I Yang - International Conference on Machine …, 2022 - proceedings.mlr.press
We propose computationally tractable accelerated first-order methods for Riemannian
optimization, extending the Nesterov accelerated gradient (NAG) method. For both …

Autonomous retrosynthesis of gold nanoparticles via spectral shape matching

K Vaddi, HT Chiang, LD Pozzo - Digital Discovery, 2022 - pubs.rsc.org
Synthesizing complex nanostructures and assemblies in experiments involves careful tuning
of design factors to obtain a suitable set of reaction conditions. In this paper, we study the …

Small transformers compute universal metric embeddings

A Kratsios, V Debarnot, I Dokmanić - Journal of Machine Learning …, 2023 - jmlr.org
We study representations of data from an arbitrary metric space χ in the space of univariate
Gaussian mixtures equipped with a transport metric (Delon and Desolneux 2020). We prove …