Scientific computing

Developing an algebraic multigrid solver in JAX
Student project
This project aims to develop a high-performance algebraic multigrid (AMG) solver in JAX that supports automatic differentiation and GPU acceleration, addressing critical gaps in existing Python and Julia implementations. The work will enable efficient gradient-based optimization in scientific machine learning applications requiring large-scale linear system solves, with potential to significantly impact the JAX ecosystem for differentiable physics simulations and inverse problems.
Nov 19, 2025
Developing an algebraic multigrid solver in JAX
Differentiable Programming for Differential Equations: A Review
Peer-reviewed
Accepted at SIAM Review.
2025 arXiv
F. Sapienza, J. Bolibar, F. Schäfer, B. Groenke, A. Pal, Victor Boussange, P. Heimbach, G. Hooker, F. Pérez, P. O. Persson, C. Rackauckas
PDF DOI
Deep learning approximations for non-local nonlinear PDEs with Neumann boundary conditions
Peer-reviewed
2022 Partial Differential Equations and Applications
Victor Boussange, Sebastian Becker, Arnulf Jentzen, Benno Kuckuck, Loïc Pellissier
PDF Cite Code
Deep learning approximations for non-local nonlinear PDEs with Neumann boundary conditions
Episodic mineralising fluid injection through chemical shear zones
Conference paper
2018 Australian Society of Exploration Geophysicists Extended Abstracts
T. Poulet, S. Alevizos, M. Veveakis, Victor Boussange, K. Regenauer-Lieb
PDF