mlsanityData to 14 Oct 2026

Parameter-varying neural ordinary differential equations with partition-of-unity networks

arXiv 2210.00368 ↗First posted 1 Oct 2022cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

In this study, we propose parameter-varying neural ordinary differential equations (NODEs) where the evolution of model parameters is represented by partition-of-unity networks (POUNets), a mixture of experts architecture. The proposed variant of NODEs, synthesized with POUNets, learn a meshfree partition of space and represent the evolution of ODE parameters using sets of polynomials associated to each partition. We demonstrate the effectiveness of the proposed method for three important tasks: data-driven dynamics modeling of (1) hybrid systems, (2) switching linear dynamical systems, and (3) latent dynamics for dynamical systems with varying external forcing.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 25 of its 49 references that are in the map. First posted on arXiv 1 Oct 2022.

Builds on

25 of 49 references.

References · 25

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  3. 2018Neural Ordinary Differential Equationscited by 3,779
  4. 2016HyperNetworkscited by 1,027
  5. 2019N-BEATS: Neural basis expansion analysis for interpretable time series forecastingcited by 753
  6. 2016Error bounds for approximations with deep ReLU networkscited by 574
  7. 2019Augmented Neural ODEscited by 397
  8. 2017Stable Architectures for Deep Neural Networkscited by 341
  9. 2017Beyond Finite Layer Neural Networks: Bridging Deep Architectures and Numerical Differential Equationscited by 203
  10. 2018Optimal approximation of continuous functions by very deep ReLU networkscited by 166
  11. 2020Dissecting Neural ODEscited by 153
  12. 2020Forecasting Sequential Data using Consistent Koopman Autoencoderscited by 115
13 more
  1. 2018Latent-space Physics: Towards Learning the Temporal Evolution of Fluid Flowcited by 97
  2. 2019ANODE: Unconditionally Accurate Memory-Efficient Gradients for Neural ODEscited by 84
  3. 2018Deep Dynamical Modeling and Control of Unsteady Fluid Flowscited by 68
  4. 2019Learning Compositional Koopman Operators for Model-Based Controlcited by 67
  5. 2020The gap between theory and practice in function approximation with deep neural networkscited by 54
  6. 2020Parameterized Neural Ordinary Differential Equations: Applications to Computational Physics Problemscited by 45
  7. 2016Recurrent switching linear dynamical systemscited by 35
  8. 2021Structure-preserving Sparse Identification of Nonlinear Dynamics for Data-driven Modelingcited by 27
  9. 2021Partition of unity networks: deep hp-approximationcited by 16
  10. 2021Stateful ODE-Nets using Basis Function Expansionscited by 14
  11. 2019ANODEV2: A Coupled Neural ODE Evolution Frameworkcited by 12
  12. 2019Growing axons: greedy learning of neural networks with application to function approximationcited by 6
  13. 2021Segmenting Hybrid Trajectories using Latent ODEscited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2023Semi-Supervised Learning of Dynamical Systems with Neural Ordinary Differential Equations: A Teacher-Student Model Approach
  2. 2025Symbolic Neural Ordinary Differential Equations
  3. 2026Nonlinear GENERIC-Embedded Neural Networks (N-GENNs): Learning GENERIC dynamics with non-quadratic dissipation potentials
  4. 2024Simulation-Free Training of Neural ODEs on Paired Data
  5. 2024From Fourier to Neural ODEs: Flow Matching for Modeling Complex Systems
  6. 2022Neural Ordinary Differential Equations for Nonlinear System Identification
  7. 2024Graph Neural Reaction Diffusion Models
  8. 2024Diffusion models as probabilistic neural operators for recovering unobserved states of dynamical systems