Mar 2 – 4, 2026
Karlsruhe Institute of Technology
Europe/Berlin timezone

Neural semi-Lagrangian method for high-dimensional advection-diffusion problems

Mar 2, 2026, 6:15 PM
3m
Triangel

Triangel

Kaiserstraße 93, 76133 Karlsruhe

Speaker

Laurent Navoret (University of Strasbourg, Inria)

Description

We are interested in numerically solving high-dimensional advection-diffusion equations, such as kinetic equations or parametric problems. Traditional numerical methods suffer from the curse of dimensionality, as the number of degrees of freedom grows exponentially with dimension. Recently, methods based on neural networks have proven effective in reducing the number of degrees of freedom by enriching classical approximation spaces. In this presentation, we will introduce a semi-Lagrangian neural method: at each time step, it consists of advecting the solution exactly, following the characteristic curves of the equation, and projecting it onto the neural approximation space. We provide rough error estimates and present several high-dimensional numerical experiments to evaluate the performance of the method. This is a joint work with Emmanuel Franck, Victor Michel-Dansac and Vincent Vigon.

Authors

Mr Emmanuel Franck (Inria, University of Strasbourg) Mr Victor Michel-Dansac (Inria, University of Strasbourg) Laurent Navoret (University of Strasbourg, Inria) Mr Vincent Vigon (University of Strasbourg, Inria)

Presentation materials

There are no materials yet.