A Neural Hierarchical-Matrix Preconditioner for Real-Time GPU Solves
cs.GR, cs.DC, cs.LG, cs.NA, math.NA
Submitted: 2026-05-13
Updated: 2026-09-24
Terminology
Sources
- Graph Neural Preconditioners for Iterative Solutions of Sparse Linear Systems
- A multiscale neural network based on hierarchical matrices
- Learning Greens Operators through Hierarchical Neural Networks Inspired by the Fast Multipole Method
- Hierarchical off-diagonal low-rank approximation of Hessians in inverse problems, with application to ice sheet model initializaiton
- Neural incomplete factorization: learning preconditioners for the conjugate gradient method
- Learning Preconditioner for Conjugate Gradient PDE Solvers
- Neural Operator: Graph Kernel Network for Partial Differential Equations
- Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
- Learning Algebraic Multigrid Using Graph Neural Networks
- Executable Code Actions Elicit Better LLM Agents
- Neural-HSS: Hierarchical Semi-Separable Neural PDE Solver
- Message-Passing GNNs Fail to Approximate Sparse Triangular Factorizations
- Learning from Linear Algebra: A Graph Neural Network Approach to Preconditioner Design for Conjugate Gradient Solvers
- Neural Approximate Inverse Preconditioners
- Learning Sparse Approximate Inverse Preconditioners for Conjugate Gradient Solvers on GPUs
Related papers
- SCRIPT: Scalable Diffusion Policy with Multi-stage Training for Language-driven Physics-Based Humanoid Control
- CADReasoner: Iterative Program Editing for CAD Reverse Engineering
- QuadLink: Autoregressive Quad-Dominant Mesh Generation via Point-Relation Learning
- DrawVideo: Grounded and Faithful Multi-Shot Video Generation from Storyboard Keyframe Sketches
- MotionPersona: Real-Time Locomotion Control across Personas, Bodies, and Styles
- MeshSplatBench: A Unified Benchmark for Triangle- and Mesh-Based Neural Rendering