English
Related papers

Related papers: Semi-Discrete Normalizing Flows through Differenti…

200 papers

We introduce a topology-preserving discretization for coupling incompressible fluids with thin deformable structures, achieving guaranteed leakproofness through preservation of fluid domain connectivity. Our approach leverages a stitching…

Computational Physics · Physics 2026-02-05 Jonathan Panuelos , Eitan Grinspun , David Levin

Flow-based generative modeling in continuous spaces exploit Tweedie's formula to express the denoiser (learned in training) as a score function (used in sampling). In contrast, this relation has been largely missing in the discrete setting…

Machine Learning · Computer Science 2026-05-04 Yair Shenfeld , Ricardo Baptista , Stefano Peluchetti

Volumetric shape representations have become ubiquitous in multi-view reconstruction tasks. They often build on regular voxel grids as discrete representations of 3D shape functions, such as SDF or radiance fields, either as the full shape…

Computer Vision and Pattern Recognition · Computer Science 2024-10-01 Diego Thomas , Briac Toussaint , Jean-Sebastien Franco , Edmond Boyer

Mimicking natural tessellation patterns is a fascinating multi-disciplinary problem. Geometric methods aiming at reproducing such partitions on surface meshes are commonly based on the Voronoi model and its variants, and are often faced…

Graphics · Computer Science 2018-04-25 Rhaleb Zayer , Daniel Mlakar , Markus Steinberger , Hans-Peter Seidel

Normalizing flows have shown great promise for modelling flexible probability distributions in a computationally tractable way. However, whilst data is often naturally described on Riemannian manifolds such as spheres, torii, and hyperbolic…

Machine Learning · Statistics 2020-12-10 Emile Mathieu , Maximilian Nickel

The order-$k$ Voronoi tessellation of a locally finite set $X \subseteq \mathbb{R}^n$ decomposes $\mathbb{R}^n$ into convex domains whose points have the same $k$ nearest neighbors in $X$. Assuming $X$ is a stationary Poisson point process,…

Probability · Mathematics 2019-04-26 Herbert Edelsbrunner , Anton Nikitenko

We present a novel discretization of coupled compressible fluid and thin deformable structures that provides sufficient and necessary leakproofness by preserving the path connectedness of the fluid domain. Our method employs a constrained…

Computational Physics · Physics 2025-07-25 Jonathan Panuelos , Eitan Grinspun , David Levin

Normalizing flows are generative models that provide tractable density estimation via an invertible transformation from a simple base distribution to a complex target distribution. However, this technique cannot directly model data…

Machine Learning · Statistics 2021-11-15 Brendan Leigh Ross , Jesse C. Cresswell

The Voronoi tessellation is a natural way of space segmentation, which has many applications in various fields of science and technology, as well as in social sciences and visual art. The varieties of the Voronoi tessellation methods are…

Astrophysics of Galaxies · Physics 2022-08-04 Irina Vavilova , Andrii Elyiv , Daria Dobrycheva , Olga Melnyk

Density deconvolution is the task of estimating a probability density function given only noise-corrupted samples. We can fit a Gaussian mixture model to the underlying density by maximum likelihood if the noise is normally distributed, but…

Machine Learning · Statistics 2020-07-14 Tim Dockhorn , James A. Ritchie , Yaoliang Yu , Iain Murray

Normalizing flows are an established approach for modelling complex probability densities through invertible transformations from a base distribution. However, the accuracy with which the target distribution can be captured by the…

Machine Learning · Statistics 2024-02-02 Harry Bevins , Will Handley , Thomas Gessey-Jones

Many modern applications of Bayesian inference, such as in cosmology, are based on complicated forward models with high-dimensional parameter spaces. This considerably limits the sampling of posterior distributions conditioned on observed…

Instrumentation and Methods for Astrophysics · Physics 2024-09-17 Marco Raveri , Cyrille Doux , Shivam Pandey

In many scientific applications, the target probability distribution cannot be evaluated in closed form or sampled from directly. Instead, it can often be decomposed into multiple components, some of which are accessible only through…

Methodology · Statistics 2026-03-10 Roxana Darvishi , David C. Stenning , Ted von Hippel , Owen G. Ward

Tuning of measurement models is challenging in real-world applications of sequential Monte Carlo methods. Recent advances in differentiable particle filters have led to various efforts to learn measurement models through neural networks.…

Artificial Intelligence · Computer Science 2022-03-17 Xiongjie Chen , Yunpeng Li

A longstanding open question in the field of dense disordered matter is how precisely structure and dynamics are related to each other. With the advent of machine learning, it has become possible to agnostically predict the dynamic…

Normalizing Flows are a promising new class of algorithms for unsupervised learning based on maximum likelihood optimization with change of variables. They offer to learn a factorized component representation for complex nonlinear data and,…

Machine Learning · Computer Science 2020-02-17 Reuben Feinman , Nikhil Parthasarathy

The application of Voronoi and Delaunay tessellation based methods for reconstructing continuous fields from discretely sampled data sets is discussed. The succesfull operation as ``multidimensional interpolation'' method is corroborated…

Astrophysics · Physics 2009-10-31 Rien van de Weygaert , Willem Schaap

This article describes, in elementary terms, a generic approach to produce discrete random tilings and similar random structures by using point process theory. The standard Voronoi and Delone tilings can be constructed in this way. For this…

Metric Geometry · Mathematics 2007-12-12 Kai Matzutt

Normalizing flows are constructed from a base distribution with a known density and a diffeomorphism with a tractable Jacobian. The base density of a normalizing flow can be parameterised by a different normalizing flow, thus allowing maps…

Machine Learning · Computer Science 2022-11-07 Samuel Klein , John Andrew Raine , Tobias Golling

Normalizing flows are exact-likelihood generative neural networks which approximately transform samples from a simple prior distribution to samples of the probability distribution of interest. Recent work showed that such generative models…

Machine Learning · Statistics 2020-10-27 Jonas Köhler , Leon Klein , Frank Noé