Timezone: »

Distributional Gradient Matching for Learning Uncertain Neural Dynamics Models
Lenart Treven · Philippe Wenk · Florian Dorfler · Andreas Krause

Tue Dec 07 08:30 AM -- 10:00 AM (PST) @

Differential equations in general and neural ODEs in particular are an essential technique in continuous-time system identification. While many deterministic learning algorithms have been designed based on numerical integration via the adjoint method, many downstream tasks such as active learning, exploration in reinforcement learning, robust control, or filtering require accurate estimates of predictive uncertainties. In this work, we propose a novel approach towards estimating epistemically uncertain neural ODEs, avoiding the numerical integration bottleneck. Instead of modeling uncertainty in the ODE parameters, we directly model uncertainties in the state space. Our algorithm distributional gradient matching (DGM) jointly trains a smoother and a dynamics model and matches their gradients via minimizing a Wasserstein loss. Our experiments show that, compared to traditional approximate inference methods based on numerical integration, our approach is faster to train, faster at predicting previously unseen trajectories, and in the context of neural ODEs, significantly more accurate.

Author Information

Lenart Treven (ETH Zurich)
Philippe Wenk (None)
Florian Dorfler (Swiss Federal Institute of Technology)
Andreas Krause (ETH Zurich)

More from the Same Authors