English

QuadNorm: Resolution-Robust Normalization for Neural Operators

Machine Learning 2026-05-11 v1 Computational Engineering, Finance, and Science Numerical Analysis Numerical Analysis

Abstract

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(h2)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 64264^2 to 2562256^2; 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.

Keywords

Cite

@article{arxiv.2605.07375,
  title  = {QuadNorm: Resolution-Robust Normalization for Neural Operators},
  author = {Bum Jun Kim and Makoto Kawano and Yusuke Iwasawa and Yutaka Matsuo},
  journal= {arXiv preprint arXiv:2605.07375},
  year   = {2026}
}

Comments

42 pages, 8 figures

R2 v1 2026-07-01T12:57:07.583Z