AI RESEARCH
RAPNet: Accelerating Algebraic Multigrid with Learned Sparse Corrections
arXiv CS.LG
•
ArXi:2605.26854v1 Announce Type: new The scalable solution of large sparse linear systems is a bottleneck in scientific computing and graph analysis. While algebraic multigrid (AMG) offers optimal linear scaling, its performance is severely constrained by the trade-off between the sparsity and convergence quality of coarse-grid operators. Classical AMG heuristics struggle to balance these objectives, often sacrificing stability or performance for sparsity.