AI RESEARCH
QuadNorm: Resolution-Robust Normalization for Neural Operators
arXiv CS.LG
•
ArXi:2605.07375v1 Announce Type: new 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