Understand
We introduce an approach for imposing physically informed inductive biases in learned simulation models.
- We combine graph networks with a differentiable ordinary differential equation integrator as a mechanism for predicting future states, and a Hamiltonian as an internal representation.
- We find that our approach outperforms baselines without these biases in terms of predictive accuracy, energy accuracy, and zero-shot generalization to time-step sizes and integrator orders not experienced during training.
- This advances the state-of-the-art of learned simulation, and in principle is applicable beyond physical domains.
Built on
Sam Greydanus, Misko Dzamba, and Jason Yosinski · 1906
Earlier work this paper cites.
Latent odes for irregularly-sampled time series
Yulia Rubanova, Ricky T. Q. Chen, and David Duvenaud · 1907
Earlier work this paper cites.
A symplectic integration algorithm for separable hamiltonian functions
J Candy and W Rozmus · 1991
Earlier work this paper cites.
Computational Science Stack Exchange, 2015
Test of 3rd-order vs 4th-order symplectic integrator with strange result · 2015
Earlier work this paper cites.
Similar
Interaction networks for learning about objects, relations and physics
Peter Battaglia, Razvan Pascanu, Matthew Lai, Danilo Rezende, and Koray Kavukcuoglu · 2016
Cited alongside, same era.
A compositional object-based approach to learning physical dynamics
Michael B. Chang, Tomer Ullman, Antonio Torralba, and Joshua B. Tenenbaum · 2017
Cited alongside, same era.
Graph networks as learnable physics engines for inference and control
Alvaro Sanchez-Gonzalez, Nicolas Heess, Jost Tobias Springenberg, Josh Merel, Martin Riedmiller, Raia Hadsell, and Peter Battaglia · 2018
Cited alongside, same era.
Flexible neural representation for physics prediction
Damian Mrowca, Chengxu Zhuang, Elias Wang, Nick Haber, Li Fei-Fei, Joshua B. Tenenbaum, and Daniel L. K. Yamins · 2018
Cited alongside, same era.
Then
Learning particle dynamics for manipulating rigid bodies, deformable objects, and fluids
Yunzhu Li, Jiajun Wu, Russ Tedrake, Joshua B Tenenbaum, and Antonio Torralba · 2018
Later among the works it cites.
Neural ordinary differential equations
Tian Qi Chen, Yulia Rubanova, Jesse Bettencourt, and David K Duvenaud · 2018
Later among the works it cites.
Relational inductive biases, deep learning, and graph networks
Peter W Battaglia, Jessica B Hamrick, Victor Bapst, Alvaro Sanchez-Gonzalez, Vinicius Zambaldi, Mateusz Malinowski, Andrea Tacchetti, David Raposo, Adam Santoro, Ryan Faulkner, et al · 2018
Later among the works it cites.
Differentiable physics-informed graph networks
Sungyong Seo and Yan Liu · 2019
Closest in time.
Beyond the bibliography
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…