← Search

Scott MacLachlan

3 accepted papers

2023

MG-GNN: Multigrid Graph Neural Networks for Learning Multilevel Domain Decomposition Methods

ICML 2023poster

Domain decomposition methods (DDMs) are popular solvers for discretized systems of partial differential equations (PDEs), with one-level and multilevel variants. These solvers rely on several algorithmic and mathematical parameters, prescribing overlap, subdomain boundary conditions, and other prope…

2022

Learning Interface Conditions in Domain Decomposition Solvers

NeurIPS 2022accept

Domain decomposition methods are widely used and effective in the approximation of solutions to partial differential equations. Yet the \textit{optimal} construction of these methods requires tedious analysis and is often available only in simplified, structured-grid settings, limiting their use fo…

2021

Optimization-Based Algebraic Multigrid Coarsening Using Reinforcement Learning

NeurIPS 2021poster

Large sparse linear systems of equations are ubiquitous in science and engineering, such as those arising from discretizations of partial differential equations. Algebraic multigrid (AMG) methods are one of the most common methods of solving such linear systems, with an extensive body of underlying…