Time-Reversal Symmetric ODE Network

Abstract

Time-reversal symmetry, which requires that the dynamics of a system should not change with the reversal of time axis, is a fundamental property that frequently holds in classical and quantum mechanics. In this paper, we propose a novel loss function that measures how well our ordinary differential equation (ODE) networks comply with this time-reversal symmetry; it is formally defined by the discrepancy in the time evolutions of ODE networks between forward and backward dynamics. Then, we design a new framework, which we name as Time-Reversal Symmetric ODE Networks (TRS-ODENs), that can learn the dynamics of physical systems more sample-efficiently by learning with the proposed loss function. We evaluate TRS-ODENs on several classical dynamics, and find they can learn the desired time evolution from observed noisy and complex trajectories. We also show that, even for systems that do not possess the full time-reversal symmetry, TRS-ODENs can achieve better predictive performances over baselines.

arXiv comment15 pages; accepted to NeurIPS 2020; Code is available at https://github.com/inhuh/trs-oden; v3: references added, typo corrected

References in corpus (19)

• Adam: A Method for Stochastic Optimization
• Deep Learning in Neural Networks: An Overview
• Discovering governing equations from data: Sparse identification of nonlinear dynamical systems
• Quantum-Chemical Insights from Deep Tensor Neural Networks
• Interaction Networks for Learning about Objects, Relations and Physics
• Discovering physical concepts with neural networks
• Hamiltonian Neural Networks
• Symplectic ODE-Net: Learning Hamiltonian Dynamics with Control
• AntisymmetricRNN: A Dynamical System View on Recurrent Neural Networks
• Identifying nonlinear dynamical systems via generative recurrent neural networks with applications to fMRI
• Hamiltonian Graph Networks with ODE Integrators
• Symplectic Recurrent Neural Networks
• Gaussian Process Model for Collision Dynamics of Complex Molecules
• HybridNet: Integrating Model-based and Data-driven Learning to Predict Evolution of Dynamical Systems
• Hamiltonian Generative Networks
• Neural Canonical Transformation with Symplectic Flows
• Learning a Local Symmetry with Neural-Networks
• Learning Symmetries of Classical Integrable Systems
• The Status of CPT