English
Related papers

Related papers: Turning Normalizing Flows into Monge Maps with Geo…

200 papers

Normalizing flows (NFs) have become a prominent method for deep generative models that allow for an analytic probability density estimation and efficient synthesis. However, a flow-based network is considered to be inefficient in parameter…

Machine Learning · Computer Science 2020-10-26 Sang-gil Lee , Sungwon Kim , Sungroh Yoon

Existing machine learning methods for causal inference usually estimate quantities expressed via the mean of potential outcomes (e.g., average treatment effect). However, such quantities do not capture the full information about the…

Machine Learning · Computer Science 2023-06-21 Valentyn Melnychuk , Dennis Frauen , Stefan Feuerriegel

This paper develops a fully discrete modified characteristic finite element method for a coupled system consisting of the fully nonlinear Monge-Amp\'ere equation and a transport equation. The system is the Eulerian formulation in the dual…

Numerical Analysis · Mathematics 2008-10-09 Xiaobing Feng , Michael Neilan

This paper presents a novel non-Gaussian inference algorithm, Normalizing Flow iSAM (NF-iSAM), for solving SLAM problems with non-Gaussian factors and/or non-linear measurement models. NF-iSAM exploits the expressive power of neural…

Robotics · Computer Science 2021-05-12 Qiangqiang Huang , Can Pu , Dehann Fourie , Kasra Khosoussi , Jonathan P. How , John J. Leonard

Mapping between discrete and continuous distributions is a difficult task and many have had to resort to heuristical approaches. We propose a tessellation-based approach that directly learns quantization boundaries in a continuous space,…

Machine Learning · Computer Science 2022-12-13 Ricky T. Q. Chen , Brandon Amos , Maximilian Nickel

Generating new molecules is fundamental to advancing critical applications such as drug discovery and material synthesis. Flows can generate molecules effectively by inverting the encoding process, however, existing flow models either…

Machine Learning · Computer Science 2022-10-14 Yogesh Verma , Samuel Kaski , Markus Heinonen , Vikas Garg

We propose an extension of the computational fluid mechanics approach to the Monge-Kantorovich mass transfer problem, which was developed by Benamou-Brenier. Our extension allows optimal transfer of unnormalized and unequal masses. We…

Optimization and Control · Mathematics 2019-10-23 Wilfrid Gangbo , Wuchen Li , Stanley Osher , Michael Puthawala

Diffusion models approximate the denoising distribution as a Gaussian and predict its mean, whereas flow matching models reparameterize the Gaussian mean as flow velocity. However, they underperform in few-step sampling due to…

Machine Learning · Computer Science 2025-09-03 Hansheng Chen , Kai Zhang , Hao Tan , Zexiang Xu , Fujun Luan , Leonidas Guibas , Gordon Wetzstein , Sai Bi

Generative models aim to learn the distribution of datasets, such as images, so as to be able to generate samples that statistically resemble real data. However, learning the underlying probability distribution can be very challenging and…

Machine Learning · Computer Science 2024-09-20 Zeyang Yu , Shengxi Li , Danilo Mandic

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

We propose a generative multivariate posterior sampler via flow matching. It offers a simple training objective, and does not require access to likelihood evaluation. The method learns a dynamic, block-triangular velocity field in the joint…

Machine Learning · Statistics 2026-04-02 Percy S. Zhai , So Won Jeong , Veronika Ročková

Analyzing and interpreting time-dependent stochastic data requires accurate and robust density estimation. In this paper we extend the concept of normalizing flows to so-called temporal Normalizing Flows (tNFs) to estimate time dependent…

Computational Physics · Physics 2019-12-20 Gert-Jan Both , Remy Kusters

In a celebrated paper \cite{noe2019boltzmann}, No\'e, Olsson, K\"ohler and Wu introduced an efficient method for sampling high-dimensional Boltzmann distributions arising in molecular dynamics via normalizing flow approximation of transport…

Machine Learning · Computer Science 2026-03-17 Zia Ur Rehman , Gero Friesecke

The so-called trivializing flows were proposed to speed up Hybrid Monte Carlo simulations, where the Wilson flow was used as an approximation of a trivializing map, a transformation of the gauge fields which trivializes the theory. It was…

High Energy Physics - Lattice · Physics 2023-10-06 David Albandea , Luigi Del Debbio , Pilar Hernández , Richard Kenway , Joe Marsh Rossney , Alberto Ramos

Non-equilibrium Monte Carlo simulations based on Jarzynski's equality are a well-understood method to compute differences in free energy and also to sample from a target probability distribution without the need to thermalize the system…

High Energy Physics - Lattice · Physics 2024-10-07 Andrea Bulgarelli , Elia Cellini , Alessandro Nada

Monge map refers to the optimal transport map between two probability distributions and provides a principled approach to transform one distribution to another. Neural network based optimal transport map solver has gained great attention in…

Machine Learning · Computer Science 2022-11-22 Jiaojiao Fan , Shu Liu , Shaojun Ma , Haomin Zhou , Yongxin Chen

This notebook tutorial demonstrates a method for sampling Boltzmann distributions of lattice field theories using a class of machine learning models known as normalizing flows. The ideas and approaches proposed in arXiv:1904.12072,…

Normalizing flows are a powerful technique for obtaining reparameterizable samples from complex multimodal distributions. Unfortunately current approaches fall short when the underlying space has a non trivial topology, and are only…

Machine Learning · Statistics 2020-06-12 Luca Falorsi , Patrick Forré

Neural ordinary differential equations (ODEs) provide expressive representations of invertible transport maps that can be used to approximate complex probability distributions, e.g., for generative modeling, density estimation, and Bayesian…

Machine Learning · Computer Science 2025-02-07 Youssef Marzouk , Zhi Ren , Jakob Zech

We present a framework for learning probability distributions on topologically non-trivial manifolds, utilizing normalizing flows. Current methods focus on manifolds that are homeomorphic to Euclidean space, enforce strong structural priors…

Machine Learning · Computer Science 2022-07-12 Dimitris Kalatzis , Johan Ziruo Ye , Alison Pouplin , Jesper Wohlert , Søren Hauberg