Derivation and analysis of parallel-in-time neural ordinary differential equations

DOI10.1007/S10472-020-09702-6zbMath1467.65122OpenAlexW3044635002MaRDI QIDQ2023867

Emmanuel Lorin

Publication date: 3 May 2021

Published in: Annals of Mathematics and Artificial Intelligence (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/s10472-020-09702-6

zbMATH Keywords

parareal methodneural ordinary differential equationsparallelism-in-timeresidual neural network

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Parallel numerical computation (65Y05) Numerical methods for initial value problems involving ordinary differential equations (65L05) Problem solving in the context of artificial intelligence (heuristics, search strategies, etc.) (68T20) General topics in artificial intelligence (68T01)

Uses Software

• torchdiffeq

Cites Work

• Unnamed Item
• Résolution d'EDP par un schéma en temps «pararéel »
• Adjoint Methods for Shape Optimization
• GMRES: A Generalized Minimal Residual Algorithm for Solving Nonsymmetric Linear Systems
• Gradient Convergence in Gradient methods with Errors
• A Parareal in Time Semi-implicit Approximation of the Navier-Stokes Equations
• Neural Network Learning
• Parallel Time Integration with Multigrid
• Analysis of the Parareal Time‐Parallel Time‐Integration Method

This page was built for publication: Derivation and analysis of parallel-in-time neural ordinary differential equations