English
Related papers

Related papers: Sylvester Normalizing Flows for Variational Infere…

200 papers

Flow models have rapidly become the go-to method for training and deploying large-scale generators, owing their success to inference-time flexibility via adjustable integration steps. A crucial ingredient in flow training is the choice of…

To better conform to data geometry, recent deep generative modelling techniques adapt Euclidean constructions to non-Euclidean spaces. In this paper, we study normalizing flows on manifolds. Previous work has developed flow models for…

Machine Learning · Statistics 2020-06-19 Aaron Lou , Derek Lim , Isay Katsman , Leo Huang , Qingxuan Jiang , Ser-Nam Lim , Christopher De Sa

Flow-based deep generative models learn data distributions by transforming a simple base distribution into a complex distribution via a set of invertible transformations. Due to the invertibility, such models can score unseen data samples…

Machine Learning · Computer Science 2019-06-18 Maximilian Schmidt , Marko Simic

Normalizing flows (NF) recently gained attention as a way to construct generative networks with exact likelihood calculation out of composable layers. However, NF is restricted to dimension-preserving transformations. Surjection VAE…

Machine Learning · Computer Science 2023-11-28 Paul M. Baggenstoss , Felix Govaers

We propose a unified framework that employs variational inference (VI) with (conditional) normalizing flows (NFs) to train both between-model and within-model proposals for reversible jump Markov chain Monte Carlo, enabling efficient…

Machine Learning · Statistics 2026-02-05 Pingping Yin , Xiyun Jiao

We investigate the use of normalizing flow (NF) models as flexible priors in Bayesian inference via Markov Chain Monte Carlo (MCMC) sampling for iterative Bayesian calibration. Trained on posteriors from previous analyses, these models can…

Nuclear Theory · Physics 2026-04-02 Hendrik Roch , Chun Shen

Despite their popularity, to date, the application of normalizing flows on categorical data stays limited. The current practice of using dequantization to map discrete data to a continuous space is inapplicable as categorical data has no…

Machine Learning · Computer Science 2021-01-22 Phillip Lippe , Efstratios Gavves

Generative models, particularly normalizing flows, have shown exceptional performance in learning probability distributions across various domains of physics, including statistical mechanics, collider physics, and lattice field theory. In…

Strongly Correlated Electrons · Physics 2025-01-14 Dominic Schuh , Janik Kreit , Evan Berkowitz , Lena Funcke , Thomas Luu , Kim A. Nicoli , Marcel Rodekamp

Learning the tail behavior of a distribution is a notoriously difficult problem. By definition, the number of samples from the tail is small, and deep generative models, such as normalizing flows, tend to concentrate on learning the body of…

Machine Learning · Computer Science 2022-06-28 Mike Laszkiewicz , Johannes Lederer , Asja Fischer

Uncertainty quantification provides quantitative measures on the reliability of candidate solutions of ill-posed inverse problems. Due to their sequential nature, Monte Carlo sampling methods require large numbers of sampling steps for…

Geophysics · Physics 2021-04-14 Ali Siahkoohi , Felix J. Herrmann

This paper introduces equivariant hamiltonian flows, a method for learning expressive densities that are invariant with respect to a known Lie-algebra of local symmetry transformations while providing an equivariant representation of the…

Machine Learning · Statistics 2019-10-01 Danilo Jimenez Rezende , Sébastien Racanière , Irina Higgins , Peter Toth

Bayesian methods estimate a measure of uncertainty by using the posterior distribution. One source of difficulty in these methods is the computation of the normalizing constant. Calculating exact posterior is generally intractable and we…

Machine Learning · Computer Science 2021-11-17 Farzaneh Mahdisoltani

Normalizing flows have recently demonstrated the ability to learn the Boltzmann distribution of the Hubbard model, opening new avenues for generative modeling in condensed matter physics. In this work, we investigate the steps required to…

Strongly Correlated Electrons · Physics 2026-01-27 Janik Kreit , Andrea Bulgarelli , Lena Funcke , Thomas Luu , Dominic Schuh , Simran Singh , Lorenzo Verzichelli

Generative models are a promising tool to address the sampling problem in multi-body and condensed-matter systems in the framework of statistical mechanics. In this work, we show that normalizing flows can be used to learn a transformation…

Computational Physics · Physics 2022-08-23 Alessandro Coretti , Sebastian Falkner , Phillip Geissler , Christoph Dellago

To model manifold data using normalizing flows, we employ isometric autoencoders to design embeddings with explicit inverses that do not distort the probability distribution. Using isometries separates manifold learning and density…

Machine Learning · Computer Science 2023-05-09 Eike Cramer , Felix Rauh , Alexander Mitsos , Raúl Tempone , Manuel Dahmen

We demonstrate several techniques to encourage practical uses of neural networks for fluid flow estimation. In the present paper, three perspectives which are remaining challenges for applications of machine learning to fluid dynamics are…

Fluid Dynamics · Physics 2022-05-19 Masaki Morimoto , Kai Fukami , Kai Zhang , Koji Fukagata

Conditional Normalizing Flows (CNFs) are flexible generative models capable of representing complicated distributions with high dimensionality and large interdimensional correlations, making them appealing for structured output learning.…

Computer Vision and Pattern Recognition · Computer Science 2023-09-06 Mohsen Zand , Ali Etemad , Michael Greenspan

Numerous applications of machine learning involve representing probability distributions over high-dimensional data. We propose autoregressive quantile flows, a flexible class of normalizing flow models trained using a novel objective based…

Machine Learning · Computer Science 2023-02-17 Phillip Si , Allan Bishop , Volodymyr Kuleshov

This paper presents a parameter scan technique for BSM signal models based on normalizing flow. Normalizing flow is a type of deep learning model that transforms a simple probability distribution into a complex probability distribution as…

Data Analysis, Statistics and Probability · Physics 2024-09-23 Masahiko Saito , Masahiro Morinaga , Tomoe Kishimoto , Junichi Tanaka

Normalizing flows have arisen as a tool to accelerate Monte Carlo sampling for lattice field theories. This work reviews recent progress in applying normalizing flows to 4-dimensional nonabelian gauge theories, focusing on two advancements:…

High Energy Physics - Lattice · Physics 2025-02-04 Ryan Abbott , Denis Boyda , Daniel C. Hackett , Gurtej Kanwar , Fernando Romero-López , Phiala E. Shanahan , Julian M. Urban