English
Related papers

Related papers: Implicit Riemannian Concave Potential Maps

200 papers

We study approximation of probability measures supported on $n$-dimensional manifolds embedded in $\mathbb{R}^m$ by injective flows -- neural networks composed of invertible flows and injective layers. We show that in general, injective…

Machine Learning · Computer Science 2022-06-28 Michael Puthawala , Matti Lassas , Ivan Dokmanić , Maarten de Hoop

In this paper we study nonconvex and nonsmooth multi-block optimization over Riemannian manifolds with coupled linear constraints. Such optimization problems naturally arise from machine learning, statistical learning, compressive sensing,…

Optimization and Control · Mathematics 2017-10-09 Junyu Zhang , Shiqian Ma , Shuzhong Zhang

Energy distributions of high frequency linear wave fields are often modelled in terms of flow or transport equations with ray dynamics given by a Hamiltonian vector field in phase space. Applications arise in underwater and room acoustics,…

Computational Physics · Physics 2014-08-12 David Chappell , Gregor Tanner , Niels Sondergaard , Dominik Loechel

One of the fundamental problems in machine learning is the estimation of a probability distribution from data. Many techniques have been proposed to study the structure of data, most often building around the assumption that observations…

Machine Learning · Statistics 2013-02-22 Oren Rippel , Ryan Prescott Adams

The geometry of generative models serves as the basis for interpolation, model inspection, and more. Unfortunately, most generative models lack a principal notion of geometry without restrictive assumptions on either the model or the data…

Machine Learning · Computer Science 2026-01-30 Frederik Möbius Rygaard , Shen Zhu , Yinzhu Jin , Søren Hauberg , Tom Fletcher

The isometric embedding problem for Riemannian manifolds, which connects intrinsic and extrinsic geometry, is a central question in differential geometry with deep theoretical significance and wide-ranging applications. Despite extensive…

Numerical Analysis · Mathematics 2026-02-24 Guangwei Gao , Kaibo Hu , Buyang Li , Ganghui Zhang

Continuous diffusion models are commonly acknowledged to display a deterministic probability flow, whereas discrete diffusion models do not. In this paper, we aim to establish the fundamental theory for the probability flow of discrete…

Machine Learning · Computer Science 2023-11-08 Pengze Zhang , Hubery Yin , Chen Li , Xiaohua Xie

Modern generative modeling methods have demonstrated strong performance in learning complex data distributions from clean samples. In many scientific and imaging applications, however, clean samples are unavailable, and only noisy or…

Machine Learning · Computer Science 2026-05-29 Willem Diepeveen , Oscar Leong

In earlier papers we introduced a representation of isotopy classes of compact surfaces embedded in the three-sphere by so called rectangular diagrams. The formalism proved useful for comparing Legendrian knots. The aim of this paper is to…

Geometric Topology · Mathematics 2021-03-31 Ivan Dynnikov , Maxim Prasolov

This work has two main purposes. The first aim is to study isotropic Riemannian maps as a generalization of isotropic immersions. For this purpose, the concept of isotropic Riemannian map is presented, an example is given and a…

Differential Geometry · Mathematics 2021-05-24 Gözde Özkan Tükel , Bayram Şahin , Tunahan Turhan

We propose an extremely versatile approach to address a large family of matrix nearness problems, possibly with additional linear constraints. Our method is based on splitting a matrix nearness problem into two nested optimization problems,…

Numerical Analysis · Mathematics 2025-08-14 Miryam Gnazzo , Vanni Noferini , Lauri Nyman , Federico Poloni

Large-scale dense mapping is vital in robotics, digital twins, and virtual reality. Recently, implicit neural mapping has shown remarkable reconstruction quality. However, incremental large-scale mapping with implicit neural representations…

Robotics · Computer Science 2024-04-10 Jianheng Liu , Haoyao Chen

Recently Implicit Neural Representations (INRs) gained attention as a novel and effective representation for various data types. Thus far, prior work mostly focused on optimizing their reconstruction performance. This work investigates INRs…

Image and Video Processing · Electrical Eng. & Systems 2022-08-05 Yannick Strümpler , Janis Postels , Ren Yang , Luc van Gool , Federico Tombari

We relate some basic constructions of stochastic analysis to differential geometry, via random walk approximations. We consider walks on both Riemannian and sub-Riemannian manifolds in which the steps consist of travel along either…

Differential Geometry · Mathematics 2017-05-15 Andrei Agrachev , Ugo Boscain , Robert Neel , Luca Rizzi

Modern generative models hold great promise for accelerating diverse tasks involving the simulation of physical systems, but they must be adapted to the specific constraints of each domain. Significant progress has been made for…

Machine Learning · Statistics 2025-12-19 Louis Grenioux , Leonardo Galliano , Ludovic Berthier , Giulio Biroli , Marylou Gabrié

We present a new automated method for finding integrable symplectic maps of the plane. These dynamical systems possess a hidden symmetry associated with an existence of conserved quantities, i.e. integrals of motion. The core idea of the…

Exactly Solvable and Integrable Systems · Physics 2025-10-21 Timofey Zolkin , Yaroslav Kharkov , Sergei Nagaitsev

The Euclidean space notion of convex sets (and functions) generalizes to Riemannian manifolds in a natural sense and is called geodesic convexity. Extensively studied computational problems such as convex optimization and sampling in convex…

Optimization and Control · Mathematics 2020-02-10 Navin Goyal , Abhishek Shetty

Optimal transport (OT) has recently found widespread interest in machine learning. It allows to define novel distances between probability measures, which have shown promise in several applications. In this work, we discuss how to…

Machine Learning · Computer Science 2021-10-11 Bamdev Mishra , N T V Satyadev , Hiroyuki Kasai , Pratik Jawanpuria

Implicit neural representations have emerged as a powerful tool in learning 3D geometry, offering unparalleled advantages over conventional representations like mesh-based methods. A common type of INR implicitly encodes a shape's boundary…

Computer Vision and Pattern Recognition · Computer Science 2024-10-17 Shen Fan , Przemyslaw Musialski

These notes on Riemannian geometry use the bases bundle and frame bundle, as in Geometry of Manifolds, to express the geometric structures. It has more problems and omits the background material. It starts with the definition of Riemannian…

Differential Geometry · Mathematics 2013-07-30 Richard L. Bishop