English
Related papers

Related papers: Constructive conditional normalizing flows

200 papers

In this paper we construct periodic capillarity-gravity water waves with an arbitrary bounded vorticity distribution. This is achieved by reexpressing, in the height function formulation of the water wave problem, the boundary condition…

Analysis of PDEs · Mathematics 2015-06-18 Anca-Voichita matioc , Bogdan-Vasile Matioc

Learning permutations is fundamental to sorting, ranking, and matching, but existing differentiable methods based on entropy-regularized Sinkhorn produce a single softened solution and collapse under ambiguity. We present PermFlow, a…

Machine Learning · Computer Science 2026-05-19 Yimeng Min , Carla P. Gomes

The growing integration of machine learning (ML) and artificial intelligence (AI) models into high-stakes domains such as healthcare and scientific research calls for models that are not only accurate but also interpretable. Among the…

Machine Learning · Computer Science 2025-10-23 Zhuo Cao , Xuan Zhao , Lena Krieger , Hanno Scharr , Ira Assent

Following recent work, this manuscript clarifies what the Gauss-Appell principle determines in incompressible, inviscid flow and how it connects to classical projection methods. At a fixed time, freezing the velocity and varying only the…

Fluid Dynamics · Physics 2026-04-24 Karthik Duraisamy

Flow matching trains a neural velocity field by regression against a target velocity associated with a prescribed probability path connecting a simple initial distribution to the data distribution. A central design choice is the path…

Machine Learning · Computer Science 2026-05-21 Shukai Du , Junzhe Zhang , Yiming Li

Some topological properties of stochastic flow $\varphi_t(x)$ generated by stochastic differential equation in a ${\mathbb R}^d_+$ with normal reflection at the boundary are investigated. Sobolev differentiability in initial condition is…

Probability · Mathematics 2008-10-28 Andrey Pilipenko

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

Let $A \subset \mathbb{R}^d$, $d\ge 2$, be a compact convex set and let $\mu = \varrho_0 dx$ be a probability measure on $A$ equivalent to the restriction of Lebesgue measure. Let $\nu = \varrho_1 dx$ be a probability measure on $B_r :=…

Differential Geometry · Mathematics 2008-05-12 Vladimir I. Bogachev , Alexander V. Kolesnikov

Causal inconsistency arises when the underlying causal graphs captured by generative models like \textit{Normalizing Flows} (NFs) are inconsistent with those specified in causal models like \textit{Struct Causal Models} (SCMs). This…

Machine Learning · Computer Science 2024-12-18 Qingyang Zhou , Kangjie Lu , Meng Xu

We introduce a new paradigm for generative modeling built on Continuous Normalizing Flows (CNFs), allowing us to train CNFs at unprecedented scale. Specifically, we present the notion of Flow Matching (FM), a simulation-free approach for…

Machine Learning · Computer Science 2023-02-09 Yaron Lipman , Ricky T. Q. Chen , Heli Ben-Hamu , Maximilian Nickel , Matt Le

Standard flow matching scales well but typically relies on an unstructured source distribution, limiting its ability to learn interpretable latent structure. Latent-variable models, by contrast, capture structure but often sacrifice…

Machine Learning · Computer Science 2026-05-11 Xavier Sumba , Carles Balsells-Rodas , Yingzhen Li

We present a data-driven approach for probabilistic wind power forecasting based on conditional normalizing flow (CNF). In contrast with the existing, this approach is distribution-free (as for non-parametric and quantile-based approaches)…

Systems and Control · Electrical Eng. & Systems 2022-07-20 Honglin Wen , Pierre Pinson , Jinghuan Ma , Jie Gu , Zhijian Jin

Counterfactual explanations (CFEs) are essential for interpreting black-box models, yet they often become invalid when models are slightly changed. Existing methods for generating robust CFEs are often limited to specific types of models,…

Machine Learning · Computer Science 2026-04-21 Marcin Kostrzewa , Maciej Zięba , Jerzy Stefanowski

In the framework of the theory of partially fluidized granular flows we study the formation of longitudinal structures observed experimentally by Forterre and Pouliquen in a flow down a rough inclined plane. We show that the formation of…

Materials Science · Physics 2016-08-31 Igor S. Aranson , Lev S. Tsimring

Normalizing flows are a powerful tool for generative modelling, density estimation and posterior reconstruction in Bayesian inverse problems. In this paper, we introduce proximal residual flows, a new architecture of normalizing flows.…

Machine Learning · Computer Science 2023-05-19 Johannes Hertrich

We present a variational optimization approach for the solution of a coefficient inverse problem of simultaneous reconstruction of the dielectric permittivity and conductivity functions in time-dependent Maxwell's system using limited…

Numerical Analysis · Mathematics 2026-02-23 Eric Lindström , Larisa Beilina

Let $X$ be a compact metric space and $\Phi=\{\varphi_t\}_{t\in\mathbb{R}}$ be a continuous flow on $X$. We introduce two types of topological pressure for family of discontinuous potentials $a=\{a_t\}_{t>0}$. First, define the topological…

Dynamical Systems · Mathematics 2024-03-26 Ruolan Xiong

This study analyses the main characteristics of the fully developed laminar pulsatile flow in a toroidal pipe as the governing parameters vary. A novel computational technique is developed to obtain time-periodic solutions of the…

Fluid Dynamics · Physics 2023-12-04 Valerio Lupi , J. Simon Kern , Philipp Schlatter

We introduce a Yamabe-type flow \begin{align*} \left\{ \begin{array}{ll} \frac{\partial g}{\partial t} &=(r^m_{\phi}-R^m_{\phi})g \\ \frac{\partial \phi}{\partial t} &=\frac{m}{2}(R^m_{\phi}-r^m_{\phi}) \end{array} \right. ~~\mbox{ in }M…

Differential Geometry · Mathematics 2022-08-25 Pak Tung Ho , Jinwoo Shin , Zetian Yan

We consider two laminar incompressible flows coupled by the continuous law at a fixed interface. We approach the system by one that satisfies a friction Navier law, and we show that when the friction coefficient goes to infinity, the…

Analysis of PDEs · Mathematics 2022-06-22 François Legeais , Roger Lewandowski