English
Related papers

Related papers: Neural Flows: Efficient Alternative to Neural ODEs

200 papers

Training neural ODEs on large datasets has not been tractable due to the necessity of allowing the adaptive numerical ODE solver to refine its step size to very small values. In practice this leads to dynamics equivalent to many hundreds or…

Machine Learning · Statistics 2020-06-24 Chris Finlay , Jörn-Henrik Jacobsen , Levon Nurbekyan , Adam M Oberman

Continuous deep learning architectures have recently re-emerged as Neural Ordinary Differential Equations (Neural ODEs). This infinite-depth approach theoretically bridges the gap between deep learning and dynamical systems, offering a…

Machine Learning · Computer Science 2021-01-12 Stefano Massaroli , Michael Poli , Jinkyoo Park , Atsushi Yamashita , Hajime Asama

Neural ordinary differential equations (neural ODEs) have emerged as a novel network architecture that bridges dynamical systems and deep learning. However, the gradient obtained with the continuous adjoint method in the vanilla neural ODE…

Machine Learning · Computer Science 2023-06-12 Hong Zhang , Wenjun Zhao

The well-known generalization problem hinders the application of artificial neural networks in continuous-time prediction tasks with varying latent dynamics. In sharp contrast, biological systems can neatly adapt to evolving environments…

Machine Learning · Computer Science 2025-03-10 Jindou Jia , Zihan Yang , Meng Wang , Kexin Guo , Jianfei Yang , Xiang Yu , Lei Guo

It has been observed that residual networks can be viewed as the explicit Euler discretization of an Ordinary Differential Equation (ODE). This observation motivated the introduction of so-called Neural ODEs, which allow more general…

Machine Learning · Computer Science 2021-04-21 Tianjun Zhang , Zhewei Yao , Amir Gholami , Kurt Keutzer , Joseph Gonzalez , George Biros , Michael Mahoney

Convolutional neural networks (CNNs) have been widely used over many areas in compute vision. Especially in classification. Recently, FlowNet and several works on opti- cal estimation using CNNs shows the potential ability of CNNs in doing…

Computer Vision and Pattern Recognition · Computer Science 2017-10-05 Junxuan Li

Neural Ordinary Differential Equations replace the right-hand side of a conventional ODE with a neural net, which by virtue of the universal approximation theorem, can be trained to the representation of any function. When we do not know…

Neurons and Cognition · Quantitative Biology 2020-08-25 Robert Strauss

A conventional approach to train neural ordinary differential equations (ODEs) is to fix an ODE solver and then learn the neural network's weights to optimize a target loss function. However, such an approach is tailored for a specific…

Machine Learning · Computer Science 2021-03-16 Julia Gusak , Alexandr Katrutsa , Talgat Daulbaev , Andrzej Cichocki , Ivan Oseledets

Neural ordinary differential equations (NODEs), one of the most influential works of the differential equation-based deep learning, are to continuously generalize residual networks and opened a new field. They are currently utilized for…

Machine Learning · Computer Science 2023-12-19 Woojin Cho , Seunghyeon Cho , Hyundong Jin , Jinsung Jeon , Kookjin Lee , Sanghyun Hong , Dongeun Lee , Jonghyun Choi , Noseong Park

We propose a novel second-order optimization framework for training the emerging deep continuous-time models, specifically the Neural Ordinary Differential Equations (Neural ODEs). Since their training already involves expensive gradient…

Machine Learning · Computer Science 2021-11-09 Guan-Horng Liu , Tianrong Chen , Evangelos A. Theodorou

Neural surrogates for partial differential equations (PDEs) have become popular due to their potential to quickly simulate physics. With a few exceptions, neural surrogates generally treat the forward evolution of time-dependent PDEs as a…

Machine Learning · Computer Science 2025-04-18 Anthony Zhou , Amir Barati Farimani

Neural Flows efficiently model irregular multivariate time series by directly learning ODE solution trajectories with neural networks, bypassing step-by-step numerical solvers. Despite their efficiency, many existing approaches treat…

Machine Learning · Computer Science 2026-05-12 Mengzhou Gao , Kaiwei Wang , Pengfei Jiao

In this work, we propose a parallel-in-time solver for linear and nonlinear ordinary differential equations. The approach is based on an efficient multilevel solver of the Schur complement related to a multilevel time partition. For linear…

Numerical Analysis · Mathematics 2017-09-20 Santiago Badia , Marc Olm

Classical neural ordinary differential equations (ODEs) are powerful tools for approximating the log-density functions in high-dimensional spaces along trajectories, where neural networks parameterize the velocity fields. This paper…

Optimization and Control · Mathematics 2025-01-30 Mo Zhou , Stanley Osher , Wuchen Li

Normalizing flows are powerful non-parametric statistical models that function as a hybrid between density estimators and generative models. Current learning algorithms for normalizing flows assume that data points are sampled…

Machine Learning · Computer Science 2023-05-31 Matthias Kirchler , Christoph Lippert , Marius Kloft

Efficient gradient computation of the Jacobian determinant term is a core problem in many machine learning settings, and especially so in the normalizing flow framework. Most proposed flow models therefore either restrict to a function…

Machine Learning · Computer Science 2021-06-10 T. Anderson Keller , Jorn W. T. Peters , Priyank Jaini , Emiel Hoogeboom , Patrick Forré , Max Welling

There has been much research on network flows over time due to their important role in real world applications. This has led to many results, but the more challenging continuous time model still lacks some of the key concepts and techniques…

Systems and Control · Computer Science 2014-01-24 Ebrahim Nasrabadi , Ronald Koch

Differential equations parameterized by neural networks become expensive to solve numerically as training progresses. We propose a remedy that encourages learned dynamics to be easier to solve. Specifically, we introduce a differentiable…

Machine Learning · Computer Science 2020-10-26 Jacob Kelly , Jesse Bettencourt , Matthew James Johnson , David Duvenaud

Recurrent neural networks (RNNs) have been used extensively and with increasing success to model various types of sequential data. Much of this progress has been achieved through devising recurrent units and architectures with the…

Machine Learning · Statistics 2017-03-06 Yacine Jernite , Edouard Grave , Armand Joulin , Tomas Mikolov

Data-driven modeling of dynamical systems is a crucial area of machine learning. In many scenarios, a thorough understanding of the model's behavior becomes essential for practical applications. For instance, understanding the behavior of a…

Machine Learning · Computer Science 2025-04-14 Krzysztof Kacprzyk , Mihaela van der Schaar