Identifying Physical Law of Hamiltonian Systems via Meta-Learning
arXiv:2102.11544
Abstract
Hamiltonian mechanics is an effective tool to represent many physical processes with concise yet well-generalized mathematical expressions. A well-modeled Hamiltonian makes it easy for researchers to analyze and forecast many related phenomena that are governed by the same physical law. However, in general, identifying a functional or shared expression of the Hamiltonian is very difficult. It requires carefully designed experiments and the researcher's insight that comes from years of experience. We propose that meta-learning algorithms can be potentially powerful data-driven tools for identifying the physical law governing Hamiltonian systems without any mathematical assumptions on the representation, but with observations from a set of systems governed by the same physical law. We show that a well meta-trained learner can identify the shared representation of the Hamiltonian by evaluating our method on several types of physical systems with various experimental settings.
arXiv commentICLR 2021
References in corpus (14)
- Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
- Prototypical Networks for Few-shot Learning
- Discovering governing equations from data: Sparse identification of nonlinear dynamical systems
- Meta-SGD: Learning to Learn Quickly for Few-Shot Learning
- Interaction Networks for Learning about Objects, Relations and Physics
- On First-Order Meta-Learning Algorithms
- Learning to Simulate Complex Physics with Graph Networks
- Discovering Symbolic Models from Deep Learning with Inductive Biases
- DeepMoD: Deep learning for Model Discovery in noisy data
- Hamiltonian Graph Networks with ODE Integrators
- Dissipative SymODEN: Encoding Hamiltonian Dynamics with Dissipation and Control into Deep Learning
- Learning Symbolic Physics with Graph Networks
- Data-driven discovery of free-form governing differential equations
- Meta-Learning Symmetries by Reparameterization