Universality and Generalization of Causal Transformers Across Context Lengths
cs.LG, math.OC, stat.ML
Submitted: 2026-09-28
Updated: 2026-09-28
Code: https://github.com/gpeyre/transformers-universality
Terminology
Sources
- Irregularities and Scaling in Signal and Image Processing: Multifractal Analysis
- Longformer: The Long-Document Transformer
- Extending Context Window of Large Language Models via Positional Interpolation
- Estimators of Fractal Dimension: Assessing the Roughness of Time Series and Spatial Data
- Data Complexity Estimates for Operator Learning
- Optimal classification and nonparametric regression for functional data
- A Mathematical Theory of Attention
- Parrot Mind: Towards Explaining the Complex Task Reasoning of Pretrained Large Language Models with Template-Content Structure
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks