Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

QuadNorm: Resolution-Robust Normalization for Neural Operators

About

Normalization layers in neural operators usually compute statistics by uniformly averaging discrete grid values, making the normalization itself discretization-dependent and thereby a source of transfer error across different resolutions or meshes. To enable discretization robustness, we introduce a quadrature normalization family that replaces existing uniform averaging in normalization layers with numerical quadrature: QuadNorm and BlendQuadNorm. On endpoint-inclusive uniform grids, the proposed quadrature moments are $O(h^2)$-consistent across discretizations, meaning that their cross-resolution mismatch decays quadratically with grid spacing. A transfer-error bound then predicts how normalization-induced mismatch scales with both the resolution gap and network depth. The experiments show the same gap- and depth-scaling trends predicted by the transfer-error bound. On Darcy, QuadNorm delivers the best cross-resolution performance at every tested target resolution from $64^2$ to $256^2$; on real-data benchmarks, Transolver with QuadNorm achieves nearly resolution-invariant transfer. The largest gains appear on nonperiodic PDEs and nonspectral architectures, where native-resolution improvements also emerge. We also validate BlendQuadNorm, which stays close to LayerNorm behavior and serves as a conservative default for periodic FNO settings. These results identify normalization as a previously overlooked source of resolution dependence in neural operators.

Bum Jun Kim, Makoto Kawano, Yusuke Iwasawa, Yutaka Matsuo• 2026

Related benchmarks

TaskDatasetResultRank
PDE solvingDarcy
Relative L2 Error3.78
46
Forward PDE solvingElasticity
Relative L2 Error9.72
44
PDE solvingDarcy Flow 64x64 resolution
Relative L2 Error0.0561
27
PDE solvingDarcy Flow 128x128 resolution
Relative L2 Error6.19
17
PDE solvingDarcy Flow 256x256 resolution
Relative L2 Error6.66
17
PDE solvingDarcy Flow 32x32 resolution
Relative L2 Error0.0327
17
Fluid Flow PredictionDarcy Flow 700 train and 200 test examples official FNO (test)
Relative L2 Error6.32
15
PDE solvingFNO Darcy 64² → 128² resolution official (test)
Relative L2 Error3.08
12
PDE solvingFNO Darcy 64² → 256² resolution official (test)
Relative L2 Error3.4
12
PDE solvingCavity flow
Relative L2 Error1.3
12
Showing 10 of 15 rows

Other info

Follow for update