Proximal Implicit ODE Solvers for Accelerating Learning Neural ODEs

04/19/2022
by   Justin Baker, et al.
3

Learning neural ODEs often requires solving very stiff ODE systems, primarily using explicit adaptive step size ODE solvers. These solvers are computationally expensive, requiring the use of tiny step sizes for numerical stability and accuracy guarantees. This paper considers learning neural ODEs using implicit ODE solvers of different orders leveraging proximal operators. The proximal implicit solver consists of inner-outer iterations: the inner iterations approximate each implicit update step using a fast optimization algorithm, and the outer iterations solve the ODE system over time. The proximal implicit ODE solver guarantees superiority over explicit solvers in numerical stability and computational efficiency. We validate the advantages of proximal implicit solvers over existing popular neural ODE solvers on various challenging benchmark tasks, including learning continuous-depth graph neural networks and continuous normalizing flows.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/04/2022

Efficient implicit solvers for models of neuronal networks

We introduce economical versions of standard implicit ODE solvers that a...
research
05/13/2017

A shortcut for IMEX methods: integrate the residual explicitly

In numerical time-integration with implicit-explicit (IMEX) methods, a w...
research
11/09/2020

Inexact Methods for Sequential Fully Implicit (SFI) Reservoir Simulation

The sequential fully implicit (SFI) scheme was introduced (Jenny et al. ...
research
06/07/2023

Comparison of SeDuMi and SDPT3 Solvers for Stability of Continuous-time Linear System

SeDuMi and SDPT3 are two solvers for solving Semi-definite Programming (...
research
08/07/2022

Accelerating Numerical Solvers for Large-Scale Simulation of Dynamical System via NeurVec

Ensemble-based large-scale simulation of dynamical systems is essential ...
research
06/04/2021

Contracting Neural-Newton Solver

Recent advances in deep learning have set the focus on neural networks (...
research
04/02/2021

Two-Stage Gauss–Seidel Preconditioners and Smoothers for Krylov Solvers on a GPU cluster

Gauss-Seidel (GS) relaxation is often employed as a preconditioner for a...

Please sign up or login with your details

Forgot password? Click here to reset