Generalization bounds for neural ordinary differential equations and deep residual networks
P Marion - Advances in Neural Information Processing …, 2024 - proceedings.neurips.cc
Neural ordinary differential equations (neural ODEs) are a popular family of continuous-
depth deep learning models. In this work, we consider a large family of parameterized ODEs …
depth deep learning models. In this work, we consider a large family of parameterized ODEs …
Generalizing to new physical systems via context-informed dynamics model
Data-driven approaches to modeling physical systems fail to generalize to unseen systems
that share the same general dynamics with the learning domain, but correspond to different …
that share the same general dynamics with the learning domain, but correspond to different …
Machine Learning with Physics Knowledge for Prediction: A Survey
This survey examines the broad suite of methods and models for combining machine
learning with physics knowledge for prediction and forecast, with a focus on partial …
learning with physics knowledge for prediction and forecast, with a focus on partial …
MetaNO: How to transfer your knowledge on learning hidden physics
Gradient-based meta-learning methods have primarily been applied to classical machine
learning tasks such as image classification. Recently, partial differential equation (PDE) …
learning tasks such as image classification. Recently, partial differential equation (PDE) …
Spatio-temporal fluid dynamics modeling via physical-awareness and parameter diffusion guidance
H Wu, F Xu, Y Duan, Z Niu, W Wang, G Lu… - arxiv preprint arxiv …, 2024 - arxiv.org
This paper proposes a two-stage framework named ST-PAD for spatio-temporal fluid
dynamics modeling in the field of earth sciences, aiming to achieve high-precision …
dynamics modeling in the field of earth sciences, aiming to achieve high-precision …
Towards cross domain generalization of hamiltonian representation via meta learning
Recent advances in deep learning for physics have focused on discovering shared
representations of target systems by incorporating physics priors or inductive biases into …
representations of target systems by incorporating physics priors or inductive biases into …
Interpretable meta-learning of physical systems
Machine learning methods can be a valuable aid in the scientific process, but they need to
face challenging settings where data come from inhomogeneous experimental conditions …
face challenging settings where data come from inhomogeneous experimental conditions …
[PDF][PDF] Stochastic neural simulator for generalizing dynamical systems across environments
J Liu, J Cui, J Yang, B Yang - Proceedings of the Thirty-Third International …, 2024 - ijcai.org
Neural simulators for modeling complex dynamical systems have been extensively studied
for various real-world applications, such as weather forecasting, ocean current prediction …
for various real-world applications, such as weather forecasting, ocean current prediction …
Neural Context Flows for Meta-Learning of Dynamical Systems
Neural Ordinary Differential Equations (NODEs) often struggle to adapt to new dynamic
behaviors caused by parameter changes in the underlying system, even when these …
behaviors caused by parameter changes in the underlying system, even when these …
Learning Interpretable Hierarchical Dynamical Systems Models from Time Series Data
In science, we are often interested in obtaining a generative model of the underlying system
dynamics from observed time series. While powerful methods for dynamical systems …
dynamics from observed time series. While powerful methods for dynamical systems …