High-Dimensional Learning Dynamics of Attention-Indexed Models
cs.LG, stat.ML
Submitted: 2026-09-03
Updated: 2026-09-03
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Escape dynamics and implicit bias of one-pass SGD in overparameterized quadratic networks
- Scaling Laws and Spectra of Shallow Neural Networks in the Feature Learning Regime
- Statistical Advantage of Softmax Attention: Insights from Single-Location Regression
- High-Dimensional Analysis of Gradient Flow for Extensive-Width Quadratic Neural Networks
- Neural Quadratic Forms: A Unified Minimal Model for Sudden Learning and Scaling Laws
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: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks