English
Related papers

Related papers: Variational Mixture of Normalizing Flows

200 papers

The use of machine learning to generate synthetic data has grown in popularity with the proliferation of text-to-image models and especially large language models. The core methodology these models use is to learn the distribution of the…

Statistical Finance · Quantitative Finance 2023-11-28 Ruslan Tepelyan , Achintya Gopal

The sampling of probability distributions specified up to a normalization constant is an important problem in both machine learning and statistical mechanics. While classical stochastic sampling methods such as Markov Chain Monte Carlo…

Machine Learning · Statistics 2020-10-27 Hao Wu , Jonas Köhler , Frank Noé

Recently normalizing flows (NFs) have demonstrated state-of-the-art performance on modeling 3D point clouds while allowing sampling with arbitrary resolution at inference time. However, these flow-based models still require long training…

Computer Vision and Pattern Recognition · Computer Science 2021-12-01 Janis Postels , Mengya Liu , Riccardo Spezialetti , Luc Van Gool , Federico Tombari

Without any assumptions about data generation, multiple causal models may explain our observations equally well. To avoid selecting a single arbitrary model that could result in unsafe decisions if it does not match reality, it is therefore…

Machine Learning · Computer Science 2025-01-13 Tristan Deleu

The normalization constraint on probability density poses a significant challenge for solving the Fokker-Planck equation. Normalizing Flow, an invertible generative model leverages the change of variables formula to ensure probability…

Machine Learning · Computer Science 2023-09-28 Feng Liu , Faguo Wu , Xiao Zhang

Mixture Density Networks are a tried and tested tool for modelling conditional probability distributions. As such, they constitute a great baseline for novel approaches to this problem. In the standard formulation, an MDN takes some input…

Machine Learning · Computer Science 2020-03-13 Jakob Kruse

This paper shows that deep learning (DL) representations of data produced by generative adversarial nets (GANs) are random vectors which fall within the class of so-called \textit{concentrated} random vectors. Further exploiting the fact…

Machine Learning · Computer Science 2020-01-24 Mohamed El Amine Seddik , Cosme Louart , Mohamed Tamaazousti , Romain Couillet

The mean-field theory for two-layer neural networks considers infinitely wide networks that are linearly parameterized by a probability measure over the parameter space. This nonparametric perspective has significantly advanced both the…

Machine Learning · Computer Science 2025-08-08 Sinho Chewi , Philippe Rigollet , Yuling Yan

A conventional Bayesian approach to prediction uses the posterior distribution to integrate out parameters in a density for unobserved data conditional on the observed data and parameters. When the true posterior is intractable, it is…

Methodology · Statistics 2026-02-27 Lucas Kock , Scott A. Sisson , G. S. Rodrigues , David J. Nott

Real-world data with underlying structure, such as pictures of faces, are hypothesized to lie on a low-dimensional manifold. This manifold hypothesis has motivated state-of-the-art generative algorithms that learn low-dimensional data…

Machine Learning · Statistics 2022-04-28 Edmond Cunningham , Renos Zabounidis , Abhinav Agrawal , Madalina Fiterau , Daniel Sheldon

Normalizing Flows (NFs) are flexible explicit generative models that have been shown to accurately model complex real-world data distributions. However, their invertibility constraint imposes limitations on data distributions that reside on…

Computer Vision and Pattern Recognition · Computer Science 2022-08-19 Janis Postels , Martin Danelljan , Luc Van Gool , Federico Tombari

The recently proposed generative flow networks (GFlowNets) are a method of training a policy to sample compositional discrete objects with probabilities proportional to a given reward via a sequence of actions. GFlowNets exploit the…

Machine Learning · Computer Science 2024-02-27 Daniil Tiapkin , Nikita Morozov , Alexey Naumov , Dmitry Vetrov

In this work, we demonstrate how to reliably estimate epistemic uncertainty while maintaining the flexibility needed to capture complicated aleatoric distributions. To this end, we propose an ensemble of Normalizing Flows (NF), which are…

Machine Learning · Computer Science 2023-10-05 Lucas Berry , David Meger

Modeling uncertainty in deep neural networks, despite recent important advances, is still an open problem. Bayesian neural networks are a powerful solution, where the prior over network weights is a design choice, often a normal…

Machine Learning · Statistics 2019-10-29 Raanan Y. Rohekar , Yaniv Gurwicz , Shami Nisimov , Gal Novik

The article develops a hybrid Variational Bayes algorithm that combines the mean-field and fixed-form Variational Bayes methods. The new estimation algorithm can be used to approximate any posterior without relying on conjugate priors. We…

Methodology · Statistics 2013-08-09 David J Nott , Minh-Ngoc Tran , Anthony Y. C. Kuk , Robert Kohn

This paper introduces a new latent variable generative model able to handle high dimensional longitudinal data and relying on variational inference. The time dependency between the observations of an input sequence is modelled using…

Machine Learning · Statistics 2023-03-28 Clément Chadebec , Stéphanie Allassonnière

From medical diagnosis to autonomous vehicles, critical applications rely on the integration of multiple heterogeneous data modalities. Multimodal Variational Autoencoders offer versatile and scalable methods for generating unobserved…

Machine Learning · Computer Science 2025-02-07 Agathe Senellart , Stéphanie Allassonnière

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

Each training step for a variational autoencoder (VAE) requires us to sample from the approximate posterior, so we usually choose simple (e.g. factorised) approximate posteriors in which sampling is an efficient computation that fully…

Machine Learning · Statistics 2018-05-29 Laurence Aitchison , Vincent Adam , Srinivas C. Turaga

Variational Bayesian Inference is a popular methodology for approximating posterior distributions over Bayesian neural network weights. Recent work developing this class of methods has explored ever richer parameterizations of the…

‹ Prev 1 8 9 10 Next ›