QuadNorm uses quadrature-based moments instead of uniform averaging in normalization layers, achieving O(h²) consistency across resolutions and better cross-resolution transfer in neural operators.
Worrall, and Max Welling
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Exact repair operators aligned with the target data manifold improve rollout accuracy in physical forecasting, while approximate repairs can increase error despite lowering constraint violations.
citing papers explorer
-
QuadNorm: Resolution-Robust Normalization for Neural Operators
QuadNorm uses quadrature-based moments instead of uniform averaging in normalization layers, achieving O(h²) consistency across resolutions and better cross-resolution transfer in neural operators.
-
Exactness Matters for Physical Rule Enforcement
Exact repair operators aligned with the target data manifold improve rollout accuracy in physical forecasting, while approximate repairs can increase error despite lowering constraint violations.