Lune

ICML2024Top-tier venue

Self-Supervised Coarsening of Unstructured Grid with Automatic Differentiation

Sergei Shumilin, Alexander Ryabov, Nikolay B. Yavich, Evgeny Burnaev, Vladimir Vanovskiy

Abstract

Due to the high computational load of modern numerical simulation, there is a demand for approaches that would reduce the size of discrete problems while keeping the accuracy reasonable. In this work, we present an original algorithm to coarsen an unstructured grid based on the concepts of differentiable physics. We achieve this by employing k-means clustering, autodifferentiation and stochastic minimization algorithms. We demonstrate performance of the designed algorithm on two PDEs: a linear parabolic equation which governs slightly compressible fluid flow in porous media and the wave equation. Our results show that in the considered scenarios, we reduced the number of grid points up to 10 times while preserving the modeled variable dynamics in the points of interest. The proposed approach can be applied to the simulation of an arbitrary system described by evolutionary partial differential equations.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

Builds onCited byLeft to right by year; the more cited, the higher.

Builds on2

  1. Learning to Control PDEs with Differentiable PhysicsPhilipp Holl, Nils Thuerey, Vladlen KoltunICLR 2020 · 221 citations
  2. JAX MD: A Framework for Differentiable PhysicsSamuel S. Schoenholz, Ekin Dogus CubukNeurIPS 2020 · 195 citations

Related papers

  1. Learnable-Differentiable Finite Volume Solver for Accelerated Simulation of FlowsMengtao Yan, Qi Wang, Haining Wang, Ruizhi Chengze et al.KDD 2025 · 3 citations
  2. PRDP: Progressively Refined Differentiable PhysicsKanishk Bhatia, Felix Koehler, Nils ThuereyICLR 2025
  3. Low-Rank Registration Based Manifolds for Convection-Dominated PDEsRambod Mojgani, Maciej BalajewiczAAAI 2021 · 25 citations
  4. NeuralStagger: Accelerating Physics-constrained Neural PDE Solver with Spatial-temporal DecompositionXinquan Huang, Wenlei Shi, Qi Meng, Yue Wang et al.ICML 2023 · 15 citations
  5. Metamizer: A Versatile Neural Optimizer for Fast and Accurate Physics SimulationsNils Wandel, Stefan Schulz, Reinhard KleinICLR 2025
Dusk over the sea between two cliffs drawn in fine vertical lines