English
Related papers

Related papers: Constructive conditional normalizing flows

200 papers

We present a method for conditional sampling for pre-trained normalizing flows when only part of an observation is available. We derive a lower bound to the conditioning variable log-probability using Schur complement properties in the…

Machine Learning · Statistics 2021-10-18 Vincent Moens , Aivar Sootla , Haitham Bou Ammar , Jun Wang

Through examples of coordinate and probability transformation between different distributions, the basic principle of normalizing flow is introduced in a simple and concise manner. From the perspective of the distribution of random variable…

Machine Learning · Computer Science 2024-01-22 Hongjun Zhang

The scaling properties of quantum gravity are discussed by employing a class of proper-time regulators in the functional flow equation for the conformal factor within the formalism of the background field method. Renormalization group…

High Energy Physics - Theory · Physics 2013-12-10 Alfio Bonanno , Filippo Guarnieri

We posit that autoregressive flow models are well-suited to performing a range of causal inference tasks - ranging from causal discovery to making interventional and counterfactual predictions. In particular, we exploit the fact that…

Machine Learning · Statistics 2020-07-28 Ricardo Pio Monti , Ilyes Khemakhem , Aapo Hyvarinen

For a topological flow $(V,\phi)$ - i.e., $V$ is a linearly compact vector space and $\phi$ a continuous endomorphism of $V$ - we gain a deep understanding of the relationship between $(V,\phi)$ and the Bernoulli shift: a topological flow…

Group Theory · Mathematics 2021-01-22 Ilaria Castellano

We adapt the precise definition of the flowing effective action in order to obtain a functional flow equation with simple properties close to physical intuition. The simplified flow equation is invariant under local gauge transformations…

High Energy Physics - Theory · Physics 2025-04-09 C. Wetterich

Long-time and large-data existence of weak solutions for initial- and boundary-value problems concerning three-dimensional flows of \emph{incompressible} fluids is nowadays available not only for Navier--Stokes fluids but also for various…

Analysis of PDEs · Mathematics 2023-08-16 Miroslav Bulíček , Josef Málek , Erika Maringová

We present $\nu$-Flows, a novel method for restricting the likelihood space of neutrino kinematics in high energy collider experiments using conditional normalizing flows and deep invertible neural networks. This method allows the recovery…

High Energy Physics - Phenomenology · Physics 2023-07-19 Matthew Leigh , John Andrew Raine , Knut Zoch , Tobias Golling

We introduce Prior-Informed Flow Matching (PIFM), a conditional flow model for graph reconstruction. Reconstructing graphs from partial observations remains a key challenge; classical embedding methods often lack global consistency, while…

Machine Learning · Computer Science 2026-01-30 Harvey Chen , Nicolas Zilberstein , Santiago Segarra

For a conditional process of the form $(\phi \vert A_{i} \not\subset \phi)$ where $\phi$ is a determinantal process we obtain a new negative correlation inequalities. Our approach relies upon the underlying geometric structure of the…

Probability · Mathematics 2023-12-12 André Goldman

In this paper we investigate renormalisation group flows of supersymmetric minimal models generated by the boundary perturbing field (\hat G_{-1/2}\phi_{1,3}). Performing the Truncated Conformal Space Approach analysis the emerging pattern…

High Energy Physics - Theory · Physics 2008-11-26 M. Kormos

Flow matching (FM) is a family of training algorithms for fitting continuous normalizing flows (CNFs). Conditional flow matching (CFM) exploits the fact that the marginal vector field of a CNF can be learned by fitting least-squares…

Machine Learning · Statistics 2025-02-04 Ganchao Wei , Li Ma

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

Machine-learning based methods like physics-informed neural networks and physics-informed neural operators are becoming increasingly adept at solving even complex systems of partial differential equations. Boundary conditions can be…

Numerical Analysis · Mathematics 2025-10-29 Niklas Göschel , Sebastian Götschel , Daniel Ruprecht

Constructal Law states that a finite-size flow system that persists in time evolves its configuration so as to provide progressively easier access to the currents that flow through it. Classical Constructal theory derives hierarchical flow…

Dynamical Systems · Mathematics 2026-03-10 Pascal Stiefenhofer

We use a novel parameterization of the flowing Hamiltonian to show that the flow equations based on continuous unitary transformations, as proposed by Wegner, can be implemented through a nonlinear partial differential equation involving…

Other Condensed Matter · Physics 2015-06-24 J. N. Kriel , A. Y. Morozov , F. G. Scholtz

We present Causal Posterior Estimation (CPE), a novel method for Bayesian inference in simulator models, i.e., models where the evaluation of the likelihood function is intractable or too computationally expensive, but where one can…

Machine Learning · Computer Science 2025-05-28 Simon Dirmeier , Antonietta Mira

Flow matching has recently emerged as a promising alternative to diffusion-based generative models, offering faster sampling and simpler training by learning continuous flows governed by ordinary differential equations. Despite growing…

Machine Learning · Computer Science 2025-12-02 Mudit Gaur , Prashant Trivedi , Shuchin Aeron , Amrit Singh Bedi , George K. Atia , Vaneet Aggarwal

We study a one-dimensional model for heavy particles in a compressible fluid. The fluid-velocity field is modelled by a persistent Gaussian random function, and the particles are assumed to be weakly inertial. Since one-dimensional…

Fluid Dynamics · Physics 2019-08-06 J. Meibohm , B. Mehlig

A low-order finite element method is constructed and analysed for an incompressible non-Newtonian flow problem with power-law rheology. The method is based on a continuous piecewise linear approximation of the velocity field and piecewise…

Numerical Analysis · Mathematics 2021-07-28 Gabriel R. Barrenechea , Endre Suli