Physics-aware, probabilistic model order reduction with guaranteed stability
arXiv:2101.05834
Abstract
Given (small amounts of) time-series' data from a high-dimensional, fine-grained, multiscale dynamical system, we propose a generative framework for learning an effective, lower-dimensional, coarse-grained dynamical model that is predictive of the fine-grained system's long-term evolution but also of its behavior under different initial conditions. We target fine-grained models as they arise in physical applications (e.g. molecular dynamics, agent-based models), the dynamics of which are strongly non-stationary but their transition to equilibrium is governed by unknown slow processes which are largely inaccessible by brute-force simulations. Approaches based on domain knowledge heavily rely on physical insight in identifying temporally slow features and fail to enforce the long-term stability of the learned dynamics. On the other hand, purely statistical frameworks lack interpretability and rely on large amounts of expensive simulation data (long and multiple trajectories) as they cannot infuse domain knowledge. The generative framework proposed achieves the aforementioned desiderata by employing a flexible prior on the complex plane for the latent, slow processes, and an intermediate layer of physics-motivated latent variables that reduces reliance on data and imbues inductive bias. In contrast to existing schemes, it does not require the a priori definition of projection operators from the fine-grained description and addresses simultaneously the tasks of dimensionality reduction and model estimation. We demonstrate its efficacy and accuracy in multiscale physical systems of particle dynamics where probabilistic, long-term predictions of phenomena not contained in the training data are produced.
ICLR 2021
References in corpus (17)
- Auto-Encoding Variational Bayes
- Discovering governing equations from data: Sparse identification of nonlinear dynamical systems
- Quantum-Chemical Insights from Deep Tensor Neural Networks
- Deep learning for universal linear embeddings of nonlinear dynamics
- Physics-Constrained Deep Learning for High-dimensional Surrogate Modeling and Uncertainty Quantification without Labeled Data
- Discovery of Nonlinear Multiscale Systems: Sampling Strategies and Embeddings
- Variational Koopman models: slow collective variables and molecular kinetics from short off-equilibrium simulations
- Physics-Informed Probabilistic Learning of Linear Embeddings of Non-linear Dynamics With Guaranteed Stability
- Data-driven non-Markovian closure models
- Scalable Gradients for Stochastic Differential Equations
- Black box variational inference for state space models
- Physics-Aware Gaussian Processes in Remote Sensing
- Deep Lagrangian Networks: Using Physics as Model Prior for Deep Learning
- Deep Generative Markov State Models
- A physics-aware, probabilistic machine learning framework for coarse-graining high-dimensional systems in the Small Data regime
- Incorporating physical constraints in a deep probabilistic machine learning framework for coarse-graining dynamical systems
- Structured Black Box Variational Inference for Latent Time Series Models