paper-with-me

Papers

QuadNorm: Resolution-Robust Normalization for Neural Operators

2026-05-08 · Bum Jun Kim, Makoto Kawano, Yusuke Iwasawa, Yutaka Matsuo arxiv

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.

📄 PDF Abstract BibTeX arXiv:2605.07375

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Supervised Quantile Normalization for Low Rank Matrix Factorization

2020-01-01 · ICML 2020 1 · Marco Cuturi, Olivier Teboul, Jonathan Niles-Weed, Jean-Philippe Vert

Low rank matrix factorization is a fundamental building block in machine learning, used for instance to summarize gene expression profile data or word-document counts. To be robust to outliers and differences in scale ac…

Connecting the geometry and dynamics of many-body complex systems with message passing neural operators

2025-02-21 · Nicholas A. Gabriel, Neil F. Johnson, George Em Karniadakis

The relationship between scale transformations and dynamics established by renormalization group techniques is a cornerstone of modern physical theories, from fluid mechanics to elementary particle physics. Integrating r…

Inductive BiasOperator learning

Medical image super-resolution method based on dense blended attention network

2019-05-13 · Kewen Liu, Yuan Ma, Hongxia Xiong, Zejun Yan 외

In order to address the issue that medical image would suffer from severe blurring caused by the lack of high-frequency details in the process of image super-resolution reconstruction, a novel medical image super-resolut…

Image Super-ResolutionSSIMSuper-Resolution

Beyond symmetrization: effective adjacency matrices and renormalization for (un)singed directed graphs

2024-06-03 · Bruno Messias Farias de Resende

To address the peculiarities of directed and/or signed graphs, new Laplacian operators have emerged. For instance, in the case of directionality, we encounter the magnetic operator, dilation (which is underexplored), ope…

Supervised Quantile Normalization for Low-rank Matrix Approximation

2020-02-08 · Marco Cuturi, Olivier Teboul, Jonathan Niles-Weed, Jean-Philippe Vert

Low rank matrix factorization is a fundamental building block in machine learning, used for instance to summarize gene expression profile data or word-document counts. To be robust to outliers and differences in scale ac…