Neural Scaling Laws of Transformer Operator Network
stat.ML, cs.LG
Submitted: 2026-09-27
Updated: 2026-09-27
Comments: 47 pages, 5 figures
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- HAMLET: Graph Transformer Neural Operator for Partial Differential Equations
- Positional Knowledge is All You Need: Position-induced Transformer (PiT) for Operator Learning
- Function graph transformers universally approximate operators between function spaces
- Scaling Laws for Neural Language Models
- Transformer for Partial Differential Equations' Operator Learning
- Fourier Neural Operator for Parametric Partial Differential Equations
- Neural Scaling Laws of Deep ReLU and Deep Operator Network: A Theoretical Study
- Hierarchical Neural Operator Transformer with Learnable Frequency-aware Loss Prior for Arbitrary-scale Super-resolution
- FourCastNet: A Global Data-driven High-resolution Weather Model using Adaptive Fourier Neural Operators
- Transformers as Cross-Task Learners: Shared Structure Drives Sample Efficiency in In-Context Learning
- Transolver: A Fast Transformer Solver for PDEs on General Geometries
- Generalization Guarantees for Multi-Input Neural Operator Learning in Sobolev Spaces
Related papers
- Behavior of prediction performance metrics with rare events
- Optimal Estimation of Generic Dynamics by Path-Dependent Neural Jump ODEs
- A Posterior-Dynamics Framework for Imaging Inverse Problems with Pretrained Diffusion Priors
- Efficient quadratic entropy with distance sketches
- Embedding-Bias in Conditional Independence Testing
- From Log-Odds to Shapley Values: An Explanatory Geometry for the Weighted Naive Bayes Classifier