cs.LGMay 8, 2026

QuadNorm: Resolution-Robust Normalization for Neural Operators

Authors: Bum Jun KimMakoto KawanoYusuke IwasawaYutaka Matsuo

Organizations: The University of Tokyo, Japan

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.

Explore similar work

CardsList
  1. Neural Operators as Efficient Function Interpolators

    May 8, 2026Vasilis Niarchos, Angelos Sirbu, Sokratis TrifinopoulosFourier Neural OperatorsNeural Operators