English
Related papers

Related papers: Semi-Discrete Normalizing Flows through Differenti…

200 papers

Poisson point processes provide a versatile framework for modeling the distributions of random points in space. When the space is partitioned into cells, each associated with a single generating point from the Poisson process, there appears…

Numerical Analysis · Mathematics 2024-05-14 Jaume Anguera Peris , Joakim Jaldén

In this paper we investigate relationships between the volumes of cells of three-dimensional Voronoi tessellations and the lengths and areas of sections obtained by intersecting the tessellation with a randomly oriented plane. Here, in…

Statistical Mechanics · Physics 2011-10-12 L. Zaninetti , M. Ferraro

Normalizing Flows are generative models that directly maximize the likelihood. Previously, the design of normalizing flows was largely constrained by the need for analytical invertibility. We overcome this constraint by a training procedure…

Machine Learning · Computer Science 2024-04-25 Felix Draxler , Peter Sorrenson , Lea Zimmermann , Armand Rousselot , Ullrich Köthe

We present a new open source code for massive parallel computation of Voronoi tessellations(VT hereafter) in large data sets. The code is focused for astrophysical purposes where VT densities and neighbors are widely used. There are several…

Instrumentation and Methods for Astrophysics · Physics 2016-07-04 Roberto E. Gonzalez

This paper proposes a semi-conditional normalizing flow model for semi-supervised learning. The model uses both labelled and unlabeled data to learn an explicit model of joint distribution over objects and labels. Semi-conditional…

Machine Learning · Statistics 2020-06-23 Andrei Atanov , Alexandra Volokhova , Arsenii Ashukha , Ivan Sosnovik , Dmitry Vetrov

Recent work on distinct multicellular organisms has revealed a hitherto unknown type of biological noise; rather than a regular arrangement, cellular neighborhood volumes, obtained by Voronoi tessellations of the cell locations, are broadly…

Soft Condensed Matter · Physics 2024-03-12 Anand Srinivasan , Steph S. M. H. Hohn , Raymond E. Goldstein

We study the problem of learning a distribution from samples, when the underlying distribution is a mixture of product distributions over discrete domains. This problem is motivated by several practical applications such as crowd-sourcing,…

Machine Learning · Statistics 2014-05-20 Prateek Jain , Sewoong Oh

Normalizing flows, a category of probabilistic models famed for their capabilities in modeling complex data distributions, have exhibited remarkable efficacy in unsupervised anomaly detection. This paper explores the potential of…

Computer Vision and Pattern Recognition · Computer Science 2024-09-04 Yixuan Zhou , Xing Xu , Zhe Sun , Jingkuan Song , Andrzej Cichocki , Heng Tao Shen

Higher-order regularization problem formulations are popular frameworks used in machine learning, inverse problems and image/signal processing. In this paper, we consider the computational problem of finding the minimizer of the Sobolev…

Numerical Analysis · Mathematics 2023-10-20 Adrien Weihs , Jalal Fadili , Matthew Thorpe

Ray flow methods provide efficient tools for modelling wave energy transport in complex systems at high-frequencies. We compare two Petrov-Galerkin discretizations of a phase-space boundary integral model for stationary wave energy…

Computational Physics · Physics 2023-10-02 David J. Chappell , Martin Richter , Gregor Tanner

We study Flow Matching in a semi-discrete setting where a Gaussian source is transported toward a discrete target supported on finitely many points. This semi-discrete regime is the theoretical setting behind the use of Flow Matching for…

Machine Learning · Computer Science 2026-05-11 Emile Pierret , Johannes Hertrich , Samuel Hurault , Julie Delon

In this work, we approach the problem of resource allocation in a team of agents through the framework of Centroidal Voronoi Tessellations. CVTs provide a natural way to embed a desired global trend in the team through probability…

Systems and Control · Electrical Eng. & Systems 2022-12-02 Bhagyashri Telsang , Seddik Djouadi

Discretizing multi-dimensional data distributions is a fundamental step of modern indexing methods. State-of-the-art techniques learn parameters of quantizers on training data for optimal performance, thus adapting quantizers to the data.…

Machine Learning · Statistics 2019-09-02 Alexandre Sablayrolles , Matthijs Douze , Cordelia Schmid , Hervé Jégou

Vessel segmentation is an essential task in many clinical applications. Although supervised methods have achieved state-of-art performance, acquiring expert annotation is laborious and mostly limited for two-dimensional datasets with a…

Image and Video Processing · Electrical Eng. & Systems 2021-07-23 Rohit Jena , Sumedha Singla , Kayhan Batmanghelich

Learned denoisers play a fundamental role in various signal generation (e.g., diffusion models) and reconstruction (e.g., compressed sensing) architectures, whose success derives from their ability to leverage low-dimensional structure in…

Machine Learning · Computer Science 2025-08-14 Shiyu Wang , Mariam Avagyan , Yihan Shen , Arnaud Lamy , Tingran Wang , Szabolcs Márka , Zsuzsa Márka , John Wright

In this paper we address the problem of discretization in the context of learning Bayesian networks (BNs) from data containing both continuous and discrete variables. We describe a new technique for <EM>multivariate</EM> discretization,…

Artificial Intelligence · Computer Science 2013-02-01 Stefano Monti , Gregory F. Cooper

In this work, we propose a method to learn multivariate probability distributions using sample path data from stochastic differential equations. Specifically, we consider temporally evolving probability distributions (e.g., those produced…

Machine Learning · Statistics 2022-05-05 Yubin Lu , Romit Maulik , Ting Gao , Felix Dietrich , Ioannis G. Kevrekidis , Jinqiao Duan

When modeling a probability distribution with a Bayesian network, we are faced with the problem of how to handle continuous variables. Most previous work has either solved the problem by discretizing, or assumed that the data are generated…

Machine Learning · Computer Science 2013-02-21 George H. John , Pat Langley

In this paper we study a gradient flow approach to the problem of quantization of measures in one dimension. By embedding our problem in $L^2$, we find a continuous version of it that corresponds to the limit as the number of particles…

Analysis of PDEs · Mathematics 2016-01-26 Emanuele Caglioti , François Golse , Mikaela Iacobelli

Recently, there has been a surge of interest in incorporating neural networks into particle filters, e.g. differentiable particle filters, to perform joint sequential state estimation and model learning for non-linear non-Gaussian…

Machine Learning · Computer Science 2025-01-07 Xiongjie Chen , Yunpeng Li