English
Related papers

Related papers: Learning Neural Differential Algebraic Equations v…

200 papers

Deep neural operators are recognized as an effective tool for learning solution operators of complex partial differential equations (PDEs). As compared to laborious analytical and computational tools, a single neural operator can predict…

Machine Learning · Statistics 2023-02-14 Navaneeth N , Tapas Tripura , Souvik Chakraborty

Equations, particularly differential equations, are fundamental for understanding natural phenomena and predicting complex dynamics across various scientific and engineering disciplines. However, the governing equations for many complex…

Machine Learning · Computer Science 2025-04-15 Junfeng Chen , Kailiang Wu , Dongbin Xiu

In conventional ODE modelling coefficients of an equation driving the system state forward in time are estimated. However, for many complex systems it is practically impossible to determine the equations or interactions governing the…

Machine Learning · Statistics 2018-03-13 Markus Heinonen , Cagatay Yildiz , Henrik Mannerström , Jukka Intosalmi , Harri Lähdesmäki

In this study, we propose high-order implicit and semi-implicit schemes for solving ordinary differential equations (ODEs) based on Taylor series expansion. These methods are designed to handle stiff and non-stiff components within a…

Numerical Analysis · Mathematics 2024-09-19 S. Boscarino , E. Macca

Augmenting mechanistic ordinary differential equation (ODE) models with machine-learnable structures is an novel approach to create highly accurate, low-dimensional models of engineering systems incorporating both expert knowledge and…

Dynamical Systems · Mathematics 2022-06-22 Sandor Beregi , David A. W. Barton , Djamel Rezgui , Simon A. Neild

Deep learning has become a pivotal technology in fields such as computer vision, scientific computing, and dynamical systems, significantly advancing these disciplines. However, neural Networks persistently face challenges related to…

Machine Learning · Computer Science 2025-10-14 Yongshuai Liu , Lianfang Wang , Kuilin Qin , Qinghua Zhang , Faqiang Wang , Li Cui , Jun Liu , Yuping Duan , Tieyong Zeng

The existing Neural ODE formulation relies on an explicit knowledge of the termination time. We extend Neural ODEs to implicitly defined termination criteria modeled by neural event functions, which can be chained together and…

Machine Learning · Computer Science 2021-10-28 Ricky T. Q. Chen , Brandon Amos , Maximilian Nickel

We provide a comprehensive survey of splitting and composition methods for the numerical integration of ordinary differential equations (ODEs). Splitting methods constitute an appropriate choice when the vector field associated with the ODE…

Numerical Analysis · Mathematics 2009-04-11 Sergio Blanes , Fernando Casas , Ander Murua

Neural Ordinary Differential Equations (Neural ODEs) construct the continuous dynamics of hidden units using ordinary differential equations specified by a neural network, demonstrating promising results on many tasks. However, Neural ODEs…

Computer Vision and Pattern Recognition · Computer Science 2024-01-11 Haoyu Chu , Shikui Wei , Qiming Lu , Yao Zhao

In this preliminary work, we present nonstandard time-stepping strategies to solve differential equations based on the algebraic estimation method applied to the estimation of time-derivative, which provides interesting properties of…

Numerical Analysis · Mathematics 2015-09-16 Loïc Michel

We are considering differential-algebraic equations with embedded optimization criteria (DAEOs) in which the embedded optimization problem is solved by global optimization. This actually leads to differential inclusions for cases in which…

Optimization and Control · Mathematics 2023-05-10 Jens Deussen , Jonathan Hüser , Uwe Naumann

It is a general notion that, in transient stability simulations, reducing the number of algebraic variables for the differential-algebraic equations (DAE) can improve the simulation performance. Many simulation programs split algebraic…

Systems and Control · Electrical Eng. & Systems 2022-07-08 Hantao Cui

Learning large scale nonlinear ordinary differential equation (ODE) systems from data is known to be computationally and statistically challenging. We present a framework together with the adaptive integral matching (AIM) algorithm for…

Statistics Theory · Mathematics 2017-10-27 Frederik Vissing Mikkelsen , Niels Richard Hansen

Learning dynamical systems through operator-theoretic representations provides a powerful framework for analyzing complex dynamics, as spectral quantities such as eigenvalues and invariant structures encode characteristic time scales and…

Machine Learning · Statistics 2026-05-19 Thibaut Germain , Sami Chemlal , Rémi Flamary , Vladimir R. Kostic , Karim Lounici

Solving partial differential equations (PDEs) efficiently and accurately remains a cornerstone challenge in science and engineering, especially for problems involving complex geometries and limited labeled data. We introduce a Physics- and…

Machine Learning · Computer Science 2025-08-14 Subhankar Sarkar , Souvik Chakraborty

Stiff systems of ordinary differential equations (ODEs) are pervasive in many science and engineering fields, yet standard neural ODE approaches struggle to learn them. This limitation is the main barrier to the widespread adoption of…

Numerical Analysis · Mathematics 2024-10-10 Colby Fronk , Linda Petzold

Energy-Dissipative Evolutionary Deep Operator Neural Network is an operator learning neural network. It is designed to seed numerical solutions for a class of partial differential equations instead of a single partial differential equation,…

Machine Learning · Statistics 2023-06-13 Jiahao Zhang , Shiheng Zhang , Jie Shen , Guang Lin

Neural ordinary differential equations (Neural ODEs) propose the idea that a sequence of layers in a neural network is just a discretisation of an ODE, and thus can instead be directly modelled by a parameterised ODE. This idea has had…

Machine Learning · Computer Science 2024-05-07 Christina Runkel , Ander Biguri , Carola-Bibiane Schönlieb

Neural Ordinary Differential Equations (ODEs) are elegant reinterpretations of deep networks where continuous time can replace the discrete notion of depth, ODE solvers perform forward propagation, and the adjoint method enables efficient,…

Data-driven discovery of "hidden physics" -- i.e., machine learning of differential equation models underlying observed data -- has recently been approached by embedding the discovery problem into a Gaussian Process regression of spatial…

Machine Learning · Computer Science 2019-08-05 Mamikon Gulian , Maziar Raissi , Paris Perdikaris , George Karniadakis