English
Related papers

Related papers: Piecewise-constant Neural ODEs

200 papers

Stiff ordinary differential equations (ODEs) are common in many science and engineering fields, but standard neural ODE approaches struggle to accurately learn these stiff systems, posing a significant barrier to widespread adoption of…

Numerical Analysis · Mathematics 2024-12-03 Colby Fronk , Linda Petzold

Normalizing flows are a powerful technique for obtaining reparameterizable samples from complex multimodal distributions. Unfortunately current approaches fall short when the underlying space has a non trivial topology, and are only…

Machine Learning · Statistics 2020-06-12 Luca Falorsi , Patrick Forré

Normalizing flows are a powerful technique for obtaining reparameterizable samples from complex multimodal distributions. Unfortunately, current approaches are only available for the most basic geometries and fall short when the underlying…

Machine Learning · Statistics 2021-05-03 Luca Falorsi

We explore in detail a method to solve ordinary differential equations using feedforward neural networks. We prove a specific loss function, which does not require knowledge of the exact solution, to be a suitable standard metric to…

Computational Physics · Physics 2020-06-02 Liam L. H. Lau , Denis Werth

Continuous deep learning models, referred to as Neural Ordinary Differential Equations (Neural ODEs), have received considerable attention over the last several years. Despite their burgeoning impact, there is a lack of formal analysis…

Machine Learning · Computer Science 2022-07-15 Diego Manzanas Lopez , Patrick Musau , Nathaniel Hamilton , Taylor T. Johnson

Physics Informed Neural Networks is a numerical method which uses neural networks to approximate solutions of partial differential equations. It has received a lot of attention and is currently used in numerous physical and engineering…

Numerical Analysis · Mathematics 2025-07-10 Dimitrios Gazoulis , Ioannis Gkanis , Charalambos G. Makridakis

Neural Jump ODEs model the conditional expectation between observations by neural ODEs and jump at arrival of new observations. They have demonstrated effectiveness for fully data-driven online forecasting in settings with irregular and…

Machine Learning · Statistics 2025-08-19 Jakob Heiss , Florian Krach , Thorsten Schmidt , Félix B. Tambe-Ndonfack

In the era of AI, neural networks have become increasingly popular for modeling, inference, and prediction, largely due to their potential for universal approximation. With the proliferation of such deep learning models, a question arises:…

Computation · Statistics 2026-04-06 Skyler Wu , Shihao Yang , S. C. Kou

We present a new data-driven reduced-order modeling approach to efficiently solve parametrized partial differential equations (PDEs) for many-query problems. This work is inspired by the concept of implicit neural representation (INR),…

Numerical Analysis · Mathematics 2023-11-30 Tianshu Wen , Kookjin Lee , Youngsoo Choi

Neural processes (NPs) are a class of models that learn stochastic processes directly from data and can be used for inference, sampling and conditional sampling. We introduce a new NP model based on flow matching, a generative modeling…

Machine Learning · Computer Science 2026-01-01 Hussen Abu Hamad , Dan Rosenbaum

As a powerful modelling method, PieceWise Linear Neural Networks (PWLNNs) have proven successful in various fields, most recently in deep learning. To apply PWLNN methods, both the representation and the learning have long been studied. In…

Machine Learning · Computer Science 2022-06-22 Qinghua Tao , Li Li , Xiaolin Huang , Xiangming Xi , Shuning Wang , Johan A. K. Suykens

Reinforcement learning algorithms are typically designed for discrete-time dynamics, even though the underlying real-world control systems are often continuous in time. In this paper, we study the problem of continuous-time reinforcement…

Machine Learning · Computer Science 2026-03-03 Klemens Iten , Lenart Treven , Bhavya Sukhija , Florian Dörfler , Andreas Krause

We introduce probabilistic neural networks that describe unsupervised synchronous learning on an atomic Hardy space and space of bounded real analytic functions, respectively. For a stationary ergodic vector process, we prove that the…

Probability · Mathematics 2020-04-23 Kyung Soo Rim , U Jin Choi

Recurrent neural networks are a powerful tool for modeling sequential data, but the dependence of each timestep's computation on the previous timestep's output limits parallelism and makes RNNs unwieldy for very long sequences. We introduce…

Neural and Evolutionary Computing · Computer Science 2016-11-22 James Bradbury , Stephen Merity , Caiming Xiong , Richard Socher

By interpreting the forward dynamics of the latent representation of neural networks as an ordinary differential equation, Neural Ordinary Differential Equation (Neural ODE) emerged as an effective framework for modeling a system dynamics…

Machine Learning · Computer Science 2020-10-19 Daehoon Gwak , Gyuhyeon Sim , Michael Poli , Stefano Massaroli , Jaegul Choo , Edward Choi

Unlike conventional grid and mesh based methods for solving partial differential equations (PDEs), neural networks have the potential to break the curse of dimensionality, providing approximate solutions to problems where using classical…

Machine Learning · Computer Science 2023-09-01 Marc Finzi , Andres Potapczynski , Matthew Choptuik , Andrew Gordon Wilson

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

Neural Controlled Differential Equations (NCDEs) are a state-of-the-art tool for supervised learning with irregularly sampled time series (Kidger, 2020). However, no theoretical analysis of their performance has been provided yet, and it…

Machine Learning · Statistics 2024-07-03 Linus Bleistein , Agathe Guilloux

Neural ODEs are increasingly used as continuous-time models for scientific and sensor data, but unconstrained neural ODEs can drift and violate domain invariants (e.g., conservation laws), yielding physically implausible solutions. In turn,…

Machine Learning · Computer Science 2026-03-26 Fangzhou Yu , Yiqi Su , Ray Lee , Shenfeng Cheng , Naren Ramakrishnan

In this work, we investigate a method for simulation-free training of Neural Ordinary Differential Equations (NODEs) for learning deterministic mappings between paired data. Despite the analogy of NODEs as continuous-depth residual…

Machine Learning · Computer Science 2024-10-31 Semin Kim , Jaehoon Yoo , Jinwoo Kim , Yeonwoo Cha , Saehoon Kim , Seunghoon Hong