Log In Sign Up

Scalable Variational Inference for Dynamical Systems

by   Nico S. Gorbach, et al.

Gradient matching is a promising tool for learning parameters and state dynamics of ordinary differential equations. It is a grid free inference approach which for fully observable systems is at times competitive with numerical integration. However for many real-world applications, only sparse observations are available or even unobserved variables are included in the model description. In these cases most gradient matching methods are difficult to apply or simply do not provide satisfactory results. That is why despite the high computational cost numerical integration is still the gold standard in many applications. Using an existing gradient matching approach, we propose a scalable variational inference framework, which can infer states and parameters simultaneously, offers computational speedups, improved accuracy and works well even under model misspecifications in a partially observable system.


page 1

page 2

page 3

page 4


Taylor-Lagrange Neural Ordinary Differential Equations: Toward Fast Training and Evaluation of Neural ODEs

Neural ordinary differential equations (NODEs) – parametrizations of dif...

Scalable Gradients for Stochastic Differential Equations

The adjoint sensitivity method scalably computes gradients of solutions ...

Mean-Field Variational Inference for Gradient Matching with Gaussian Processes

Gradient matching with Gaussian processes is a promising tool for learni...

Numerical Method for Parameter Inference of Nonlinear ODEs with Partial Observations

Parameter inference of dynamical systems is a challenging task faced by ...

Non-Factorised Variational Inference in Dynamical Systems

We focus on variational inference in dynamical systems where the discret...

Fenrir: Physics-Enhanced Regression for Initial Value Problems

We show how probabilistic numerics can be used to convert an initial val...

Distributional Gradient Matching for Learning Uncertain Neural Dynamics Models

Differential equations in general and neural ODEs in particular are an e...