English
Related papers

Related papers: Sinusoidal Flow: A Fast Invertible Autoregressive …

200 papers

To overcome topological constraints and improve the expressiveness of normalizing flow architectures, Wu, K\"ohler and No\'e introduced stochastic normalizing flows which combine deterministic, learnable flow transformations with stochastic…

Machine Learning · Computer Science 2022-12-02 Paul Hagemann , Johannes Hertrich , Gabriele Steidl

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

An invertible function is bi-Lipschitz if both the function and its inverse have bounded Lipschitz constants. Nowadays, most Normalizing Flows are bi-Lipschitz by design or by training to limit numerical errors (among other things). In this…

Machine Learning · Computer Science 2024-03-08 Alexandre Verine , Benjamin Negrevergne , Fabrice Rossi , Yann Chevaleyre

Normalizing Flows (NF) are Generative models which transform a simple prior distribution into the desired target. They however require the design of an invertible mapping whose Jacobian determinant has to be computable. Recently introduced,…

Machine Learning · Computer Science 2025-09-18 Vincent Souveton , Arnaud Guillin , Jens Jasche , Guilhem Lavaux , Manon Michel

We show that normalising flows become pathological when used to model targets whose supports have complicated topologies. In this scenario, we prove that a flow must become arbitrarily numerically noninvertible in order to approximate the…

Machine Learning · Statistics 2021-04-26 Rob Cornish , Anthony L. Caterini , George Deligiannidis , Arnaud Doucet

A normalizing flow models a complex probability density as an invertible transformation of a simple base density. Flows based on either coupling or autoregressive transforms both offer exact density evaluation and sampling, but rely on the…

Machine Learning · Statistics 2019-12-03 Conor Durkan , Artur Bekasov , Iain Murray , George Papamakarios

Variational inference relies on flexible approximate posterior distributions. Normalizing flows provide a general recipe to construct flexible variational posteriors. We introduce Sylvester normalizing flows, which can be seen as a…

Machine Learning · Statistics 2019-02-21 Rianne van den Berg , Leonard Hasenclever , Jakub M. Tomczak , Max Welling

We introduce a method for reconstructing an infinitesimal normalizing flow given only an infinitesimal change to a (possibly unnormalized) probability distribution. This reverses the conventional task of normalizing flows -- rather than…

Machine Learning · Statistics 2020-12-04 David Pfau , Danilo Rezende

Normalizing Flows provide a principled framework for high-dimensional density estimation and generative modeling by constructing invertible transformations with tractable Jacobian determinants. We propose Fractal Flow, a novel normalizing…

Machine Learning · Statistics 2025-08-28 Binhui Zhang , Jianwei Ma

We present a computational framework for efficient learning, sampling, and distribution of general Bayesian posterior distributions. The framework leverages a machine learning approach for the construction of normalizing flows for the…

Nuclear Theory · Physics 2023-10-10 Yukari Yamauchi , Landon Buskirk , Pablo Giuliani , Kyle Godbey

Normalizing flows and variational autoencoders are powerful generative models that can represent complicated density functions. However, they both impose constraints on the models: Normalizing flows use bijective transformations to model…

Machine Learning · Computer Science 2020-11-02 Didrik Nielsen , Priyank Jaini , Emiel Hoogeboom , Ole Winther , Max Welling

The two key characteristics of a normalizing flow is that it is invertible (in particular, dimension preserving) and that it monitors the amount by which it changes the likelihood of data points as samples are propagated along the network.…

Machine Learning · Computer Science 2023-01-27 Bálint Máté , Samuel Klein , Tobias Golling , François Fleuret

We propose injective generative models called Trumpets that generalize invertible normalizing flows. The proposed generators progressively increase dimension from a low-dimensional latent space. We demonstrate that Trumpets can be trained…

Machine Learning · Computer Science 2023-07-25 Konik Kothari , AmirEhsan Khorashadizadeh , Maarten de Hoop , Ivan Dokmanić

Normalizing flows model complex probability distributions using maps obtained by composing invertible layers. Special linear layers such as masked and 1x1 convolutions play a key role in existing architectures because they increase…

Machine Learning · Computer Science 2022-09-29 Chenlin Meng , Linqi Zhou , Kristy Choi , Tri Dao , Stefano Ermon

Normalizing flows are a promising tool for modeling probability distributions in physical systems. While state-of-the-art flows accurately approximate distributions and energies, applications in physics additionally require smooth energies…

Machine Learning · Statistics 2021-12-01 Jonas Köhler , Andreas Krämer , Frank Noé

Normalizing flows learn a diffeomorphic mapping between the target and base distribution, while the Jacobian determinant of that mapping forms another real-valued function. In this paper, we show that the Jacobian determinant mapping is…

Machine Learning · Computer Science 2021-02-18 Huadong Liao , Jiawei He

Normalizing flows are a powerful class of generative models demonstrating strong performance in several speech and vision problems. In contrast to other generative models, normalizing flows are latent variable models with tractable…

Machine Learning · Computer Science 2021-08-06 Dmitry Baranchuk , Vladimir Aliev , Artem Babenko

Generative modeling seeks to uncover the underlying factors that give rise to observed data that can often be modeled as the natural symmetries that manifest themselves through invariances and equivariances to certain transformation laws.…

Machine Learning · Computer Science 2022-08-16 Avishek Joey Bose , Marcus Brubaker , Ivan Kobyzev

The choice of approximate posterior distribution is one of the core problems in variational inference. Most applications of variational inference employ simple families of posterior approximations in order to allow for efficient inference,…

Machine Learning · Statistics 2016-06-15 Danilo Jimenez Rezende , Shakir Mohamed

Normalizing flows have been successfully modeling a complex probability distribution as an invertible transformation of a simple base distribution. However, there are often applications that require more than invertibility. For instance,…

Machine Learning · Computer Science 2023-04-12 Seongmin Hong , Se Young Chun