English
Related papers

Related papers: Tails of Lipschitz Triangular Flows

200 papers

Optimal transport (OT) and Schr{\"o}dinger bridge (SB) problems have emerged as powerful frameworks for transferring probability distributions with minimal cost. However, existing approaches typically focus on endpoint matching while…

Optimization and Control · Mathematics 2025-10-09 Xu Duan , Dongmei Chen

Modern deep generative models can now produce high-quality synthetic samples that are often indistinguishable from real training data. A growing body of research aims to understand why recent methods, such as diffusion and flow matching…

Machine Learning · Computer Science 2025-12-03 Quentin Bertrand , Anne Gagneux , Mathurin Massias , Rémi Emonet

In microfluidics, varying wetting properties, expressed in terms of the local slip length, can be used to influence the flow of a liquid through a device. We study flow past surfaces on which the slip length is modulated in stripes. We find…

Soft Condensed Matter · Physics 2010-02-12 Nayaz Khalid Ahmed , Martin Hecht

We develop a semi-analytic deterministic framework for charged-particle transport with continuous slowing-down in energy and angular scattering. Directed transport and energy advection are treated by method-of-characteristics integration,…

Numerical Analysis · Mathematics 2026-02-10 Ben S. Ashby , Alex Lukyanov , Tristan Pryer

Normalizing flows can generate complex target distributions and thus show promise in many applications in Bayesian statistics as an alternative or complement to MCMC for sampling posteriors. Since no data set from the target posterior…

Machine Learning · Statistics 2021-07-19 Marylou Gabrié , Grant M. Rotskoff , Eric Vanden-Eijnden

We introduce L\'evy-Flows, a class of normalizing flow models that replace the standard Gaussian base distribution with L\'evy process-based distributions, specifically Variance Gamma (VG) and Normal-Inverse Gaussian (NIG). These…

Machine Learning · Computer Science 2026-04-02 Rachid Drissi

We investigate the use of data-driven likelihoods to bypass a key assumption made in many scientific analyses, which is that the true likelihood of the data is Gaussian. In particular, we suggest using the optimization targets of flow-based…

Cosmology and Nongalactic Astrophysics · Physics 2020-11-11 Ana Diaz Rivero , Cora Dvorkin

It was recently observed that sand flowing down a vertical tube sometimes forms a traveling density pattern in which a number of regions with high density are separated from each other by regions of low density. In this work, we consider…

Condensed Matter · Physics 2016-08-14 Jysoo Lee , Michael Leibig

We develop the theory of veering triangulations on oriented surfaces adapted to moduli spaces of half-translation surfaces. We use veering triangulations to give a coding of the Teichm\"uller flow on connected components of strata of…

Dynamical Systems · Mathematics 2019-09-04 Mark Bell , Vincent Delecroix , Vaibhav Gadre , Rodolfo Gutiérrez-Romo , Saul Schleimer

We analyze the oracle complexity of sampling from polynomially decaying heavy-tailed target densities based on running the Unadjusted Langevin Algorithm on certain transformed versions of the target density. The specific class of…

Statistics Theory · Mathematics 2022-01-21 Ye He , Krishnakumar Balasubramanian , Murat A. Erdogdu

Properties of steady compressible flow for which geometric constraints have been placed on the potential function are derived, under hypotheses on the flow density and the singular set. Some related unconstrained problems are also…

Mathematical Physics · Physics 2007-05-23 Thomas H. Otway

The aim of this work is to investigate semi-Lagrangian approximation schemes on unstructured grids for viscous transport and conservative equations with measurable coefficients that satisfy a one-sided Lipschitz condition. To establish the…

Numerical Analysis · Mathematics 2025-05-15 Fabio Camilli , Adriano Festa , Luciano Marzufero

Sampling from high-dimensional distributions is a fundamental problem in statistical research and practice. However, great challenges emerge when the target density function is unnormalized and contains isolated modes. We tackle this…

Methodology · Statistics 2023-04-11 Yixuan Qiu , Xiao Wang

Flow matching has emerged as a powerful framework for generative modeling through continuous normalizing flows. We investigate a potential topological constraint: when the prior distribution and target distribution have mismatched topology…

Machine Learning · Computer Science 2025-12-16 Congzhou M Sha

This paper proposes a Mixture Density Network specifically designed for forecasting time series that exhibit locally explosive behavior. By incorporating skewed t-distributions as mixture components, our approach offers enhanced flexibility…

Methodology · Statistics 2026-02-11 Elena Dumitrescu , Julien Peignon , Arthur Thomas

We propose a multivariate generative model to capture the complex dependence structure often encountered in business and financial data. Our model features heterogeneous and asymmetric tail dependence between all pairs of individual…

Machine Learning · Computer Science 2025-12-10 Xiangqian Sun , Xing Yan , Qi Wu

Recent works have demonstrated that the convergence rate of a nonparametric density estimator can be greatly improved by using a low-rank estimator when the target density is a convex combination of separable probability densities with…

Statistics Theory · Mathematics 2023-02-10 Robert A. Vandermeulen

Nash flows over time describe the behavior of selfish users eager to reach their destination as early as possible while traveling along the arcs of a network with capacities and transit times. Throughout the past decade, they have been…

Computer Science and Game Theory · Computer Science 2020-10-06 Leon Sering , Martin Skutella

We consider a phase field model for the flow of two partly miscible incompressible, viscous fluids of Non-Newtonian (power law) type. In the model it is assumed that the densities of the fluids are equal. We prove existence of weak…

Analysis of PDEs · Mathematics 2013-02-14 Helmut Abels , Lars Diening , Yutaka Terasawa

Recent works have proposed incorporating heavy-tailed (HT) noise into diffusion- and flow-based generative models, with the goals of better recovering the tails of target distributions and improving generative diversity. This motivation is…

Machine Learning · Computer Science 2026-05-14 Hamza Cherkaoui , Hélène Halconruy , Antonio Ocello
‹ Prev 1 3 4 5 6 7 10 Next ›