mlsanityData to 14 Oct 2026

Beyond Static Models: Hypernetworks for Adaptive and Generalizable Forecasting in Complex Parametric Dynamical Systems

arXiv 2506.19609 ↗First posted 24 Jun 2025cs.LG nlin.CD physics.comp-phcited by 0

Not on the map. Why?

Abstract (arXiv)

Dynamical systems play a key role in modeling, forecasting, and decision-making across a wide range of scientific domains. However, variations in system parameters, also referred to as parametric variability, can lead to drastically different model behavior and output, posing challenges for constructing models that generalize across parameter regimes. In this work, we introduce the Parametric Hypernetwork for Learning Interpolated Networks (PHLieNet), a framework that simultaneously learns: (a) a global mapping from the parameter space to a nonlinear embedding and (b) a mapping from the inferred embedding to the weights of a dynamics propagation network. The learned embedding serves as a latent representation that modulates a base network, termed the hypernetwork, enabling it to generate the weights of a target network responsible for forecasting the system's state evolution conditioned on the previous time history. By interpolating in the space of models rather than observations, PHLieNet facilitates smooth transitions across parameterized system behaviors, enabling a unified model that captures the dynamic behavior across a broad range of system parameterizations. The performance of the proposed technique is validated in a series of dynamical systems with respect to its ability to extrapolate in time and interpolate and extrapolate in the parameter space, i.e., generalize to dynamics that were unseen during training. Our approach outperforms state-of-the-art baselines in both short-term forecast accuracy and in capturing long-term dynamical features such as attractor statistics.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 39 of its 89 references that are in the map. First posted on arXiv 24 Jun 2025.

Builds on

39 of 89 references.

References · 39

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  2. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  3. 2020Fourier Neural Operator for Parametric Partial Differential Equationscited by 2,908
  4. 2016Neural Architecture Search with Reinforcement Learningcited by 1,499
  5. 2018An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modelingcited by 1,476
  6. 2013Generating Sequences With Recurrent Neural Networkscited by 554
  7. 2023Convolutional Neural Operators for robust and accurate learning of PDEscited by 214
  8. 2021HyperStyle: StyleGAN Inversion with HyperNetworks for Real Image Editingcited by 208
  9. 2018Data-Driven Forecasting of High-Dimensional Chaotic Systems with Long Short-Term Memory Networkscited by 155
  10. 2021Enhancing Computational Fluid Dynamics with Machine Learningcited by 138
  11. 2019Backpropagation Algorithms and Reservoir Computing in Recurrent Neural Networks for the Forecasting of Complex Spatiotemporal Dynamicscited by 134
  12. 2014Dynamic mode decomposition with controlcited by 129
27 more
  1. 2021Geometry of the Loss Landscape in Overparameterized Neural Networks: Symmetries and Invariancescited by 127
  2. 2020Transformers for Modeling Physical Systemscited by 106
  3. 2023A Brief Review of Hypernetworks in Deep Learningcited by 102
  4. 2021POD-DL-ROM: enhancing deep learning-based reduced order models for nonlinear parametrized PDEs by proper orthogonal decompositioncited by 79
  5. 2019Weight-space symmetry in deep networks gives rise to permutation saddles, connected by equal-loss valleys across the loss landscapecited by 63
  6. 2024On conditional diffusion models for PDE simulationscited by 60
  7. 2020DHP: Differentiable Meta Pruning via HyperNetworkscited by 57
  8. 2022Generalizing to New Physical Systems via Context-Informed Dynamics Modelcited by 50
  9. 2023Hypernetwork-based Meta-Learning for Low-Rank Physics-Informed Neural Networkscited by 44
  10. 2021LEADS: Learning Dynamical Systems that Generalize Across Environmentscited by 40
  11. 2021HyperPINN: Learning parameterized differential equations with physics-informed hypernetworkscited by 39
  12. 2024Parameterized Physics-informed Neural Networks for Parameterized PDEscited by 38
  13. 2020Hierarchical Deep Learning of Multiscale Differential Equation Time-Stepperscited by 37
  14. 2021Meta-Auto-Decoder for Solving Parametric Partial Differential Equationscited by 36
  15. 2020Hypersolvers: Toward Fast Continuous-Depth Modelscited by 33
  16. 2022Quadratic Approximation Manifold for Mitigating the Kolmogorov Barrier in Nonlinear Projection-Based Model Order Reductioncited by 30
  17. 2022Meta-PDE: Learning to Solve PDEs Quickly Without a Meshcited by 18
  18. 2019Supervised and Unsupervised Learning of Parameterized Color Enhancementcited by 16
  19. 2024Learning Interpretable Hierarchical Dynamical Systems Models from Time Series Datacited by 15
  20. 2023On the Limitations of Physics-informed Deep Learning: Illustrations Using First Order Hyperbolic Conservation Law-based Traffic Flow Modelscited by 14
  21. 2024CoLoRA: Continuous low-rank adaptation for reduced implicit neural modeling of parameterized partial differential equationscited by 14
  22. 2024On latent dynamics learning in nonlinear reduced order modelingcited by 14
  23. 2023Learning Parametric Koopman Decompositions for Prediction and Controlcited by 6
  24. 2024HyperCAN: Hypernetwork-Driven Deep Parameterized Constitutive Models for Metamaterialscited by 5
  25. 2023HyperLoRA for PDEscited by 4
  26. 2024Reconstructing dynamics from sparse observations with no training on target systemcited by 2
  27. 2023Stacked tensorial neural networks for reduced-order modeling of a parametric partial differential equationcited by 1

Built on by

Not cited yet.