Distributional Gradient Matching for Learning Uncertain Neural Dynamics Models

by   Lenart Treven, et al.

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.



page 33

page 34

page 41


Faster Policy Learning with Continuous-Time Gradients

We study the estimation of policy gradients for continuous-time systems ...

Approximate Numerical Integration of the Chemical Master Equation for Stochastic Reaction Networks

Numerical solution of the chemical master equation for stochastic reacti...

Discrete gradients for computational Bayesian inference

In this paper, we exploit the gradient flow structure of continuous-time...

Bayesian Algorithms Learn to Stabilize Unknown Continuous-Time Systems

Linear dynamical systems are canonical models for learning-based control...

Scalable Variational Inference for Dynamical Systems

Gradient matching is a promising tool for learning parameters and state ...

Distributional Hamilton-Jacobi-Bellman Equations for Continuous-Time Reinforcement Learning

Continuous-time reinforcement learning offers an appealing formalism for...

Distributed Distributional Deterministic Policy Gradients

This work adopts the very successful distributional perspective on reinf...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.