English
Related papers

Related papers: Towards Recurrent Autoregressive Flow Models

200 papers

Simulating turbulent flows is crucial for a wide range of applications, and machine learning-based solvers are gaining increasing relevance. However, achieving temporal stability when generalizing to longer rollout horizons remains a…

Machine Learning · Computer Science 2024-12-12 Georg Kohl , Li-Wei Chen , Nils Thuerey

Real-world data often exhibits sequential dependence, across diverse domains such as human behavior, medicine, finance, and climate modeling. Probabilistic methods capture the inherent uncertainty associated with prediction in these…

Machine Learning · Statistics 2024-03-08 Alex Boyd

Many studies on biological and soft matter systems report the joint presence of a linear mean-squared displacement and a non-Gaussian probability density exhibiting, for instance, exponential or stretched-Gaussian tails. This phenomenon is…

Statistical Mechanics · Physics 2019-07-24 Jakub Ślęzak , Krzysztof Burnecki , Ralf Metzler

Understanding the dynamics of complex molecular processes is often linked to the study of infrequent transitions between long-lived stable states. The standard approach to the sampling of such rare events is to generate an ensemble of…

Computational Physics · Physics 2023-05-22 Sebastian Falkner , Alessandro Coretti , Salvatore Romano , Phillip Geissler , Christoph Dellago

In this work, we propose FlowTime, a generative model for probabilistic forecasting of multivariate timeseries data. Given historical measurements and optional future covariates, we formulate forecasting as sampling from a learned…

Machine Learning · Computer Science 2026-02-10 Ahmed ElGazzar , Marcel van Gerven

Predicting future states or actions of a given system remains a fundamental, yet unsolved challenge of intelligence, especially in the scope of complex and non-deterministic scenarios, such as modeling behavior of humans. Existing…

Machine Learning · Computer Science 2020-12-01 Maciej Zięba , Marcin Przewięźlikowski , Marek Śmieja , Jacek Tabor , Tomasz Trzcinski , Przemysław Spurek

Causal models capture cause-effect relations both qualitatively - via the graphical causal structure - and quantitatively - via the model parameters. They offer a powerful framework for analyzing and constructing processes. Here, we…

Quantum Physics · Physics 2025-12-02 Ämin Baumeler , Stefan Wolf

Flow models are effective at progressively generating realistic images, but they generally struggle to capture long-range dependencies during the generation process as they compress all the information from previous time steps into a single…

Computer Vision and Pattern Recognition · Computer Science 2025-06-17 Mude Hui , Rui-Jie Zhu , Songlin Yang , Yu Zhang , Zirui Wang , Yuyin Zhou , Jason Eshraghian , Cihang Xie

Recently, there has been a surge of interest in incorporating neural networks into particle filters, e.g. differentiable particle filters, to perform joint sequential state estimation and model learning for non-linear non-Gaussian…

Machine Learning · Computer Science 2025-01-07 Xiongjie Chen , Yunpeng Li

Many recent machine learning models rely on fine-grained dynamic control flow for training and inference. In particular, models based on recurrent neural networks and on reinforcement learning depend on recurrence relations, data-dependent…

Distributed, Parallel, and Cluster Computing · Computer Science 2018-05-09 Yuan Yu , Martín Abadi , Paul Barham , Eugene Brevdo , Mike Burrows , Andy Davis , Jeff Dean , Sanjay Ghemawat , Tim Harley , Peter Hawkins , Michael Isard , Manjunath Kudlur , Rajat Monga , Derek Murray , Xiaoqiang Zheng

We introduce a method for learning the dynamics of complex nonlinear systems based on deep generative models over temporal segments of states and actions. Unlike dynamics models that operate over individual discrete timesteps, we learn the…

Machine Learning · Computer Science 2017-07-14 Nikhil Mishra , Pieter Abbeel , Igor Mordatch

Normalizing flows transform a simple base distribution into a complex target distribution and have proved to be powerful models for data generation and density estimation. In this work, we propose a novel type of normalizing flow driven by…

Machine Learning · Computer Science 2021-07-14 Ruizhi Deng , Bo Chang , Marcus A. Brubaker , Greg Mori , Andreas Lehrmann

Modeling complex conditional distributions is critical in a variety of settings. Despite a long tradition of research into conditional density estimation, current methods employ either simple parametric forms or are difficult to learn in…

Machine Learning · Statistics 2018-02-15 Brian L Trippe , Richard E Turner

Normalizing flows, diffusion normalizing flows and variational autoencoders are powerful generative models. This chapter provides a unified framework to handle these approaches via Markov chains. We consider stochastic normalizing flows as…

Machine Learning · Computer Science 2023-02-06 Paul Hagemann , Johannes Hertrich , Gabriele Steidl

In this study, we address causal inference when only observational data and a valid causal ordering from the causal graph are available. We introduce a set of flow models that can recover component-wise, invertible transformation of…

Machine Learning · Computer Science 2024-12-16 Minh Khoa Le , Kien Do , Truyen Tran

We formulate a new class of conditional generative models based on probability flows. Trained with maximum likelihood, it provides efficient inference and sampling from class-conditionals or the joint distribution, and does not require a…

Machine Learning · Computer Science 2019-04-23 Micha Livne , David Fleet

Forecasting neural activity in response to naturalistic stimuli remains a key challenge for understanding brain dynamics and enabling downstream neurotechnological applications. Here, we introduce a generative forecasting framework for…

Neurons and Cognition · Quantitative Biology 2026-04-14 Nicole Rogalla , Yuzhen Qin , Mario Senden , Ahmed El-Gazzar , Marcel van Gerven

We present a pseudo-reversible normalizing flow method for efficiently generating samples of the state of a stochastic differential equation (SDE) with different initial distributions. The primary objective is to construct an accurate and…

Numerical Analysis · Mathematics 2023-06-12 Minglei Yang , Pengjun Wang , Diego del-Castillo-Negrete , Yanzhao Cao , Guannan Zhang

Generative modeling provides a powerful framework for learning data distributions. These models initially relied on probabilistic methods such as Gaussian Processes (GP) for uncertainty-aware predictions and shifted towards larger trainable…

In this work, we deepen on the use of normalizing flows for causal reasoning. Specifically, we first leverage recent results on non-linear ICA to show that causal models are identifiable from observational data given a causal ordering, and…

Machine Learning · Computer Science 2023-12-11 Adrián Javaloy , Pablo Sánchez-Martín , Isabel Valera