Ising on the graph: Task-specific graph subsampling via the Ising model

M Bånkestad, JR Andersson, S Mair… - arxiv preprint arxiv …, 2024 - arxiv.org
Reducing a graph while preserving its overall structure is an important problem with many
applications. Typically, reduction approaches either remove edges (sparsification) or merge …

Neural incomplete factorization: learning preconditioners for the conjugate gradient method

P Häusner, O Öktem, J Sjölund - arxiv preprint arxiv:2305.16368, 2023 - arxiv.org
Finding suitable preconditioners to accelerate iterative solution methods, such as the
conjugate gradient method, is an active area of research. In this paper, we develop a …

Learning incomplete factorization preconditioners for GMRES

P Häusner, AN Juscafresa, J Sjölund - arxiv preprint arxiv:2409.08262, 2024 - arxiv.org
In this paper, we develop a data-driven approach to generate incomplete LU factorizations
of large-scale sparse matrices. The learned approximate factorization is utilized as a …

Advancing Heatwave Forecasting via Distribution Informed-Graph Neural Networks (DI-GNNs): Integrating Extreme Value Theory with GNNs

FA Chishtie, D Brunet, RH White, D Michelson… - arxiv preprint arxiv …, 2024 - arxiv.org
Heatwaves, prolonged periods of extreme heat, have intensified in frequency and severity
due to climate change, posing substantial risks to public health, ecosystems, and …

Deep Learning-Enhanced Preconditioning for Efficient Conjugate Gradient Solvers in Large-Scale PDE Systems

R Li, S Wang, C Wang - arxiv preprint arxiv:2412.07127, 2024 - arxiv.org
Preconditioning techniques are crucial for enhancing the efficiency of solving large-scale
linear equation systems that arise from partial differential equation (PDE) discretization …