Multi-Head Self Attention is a Parameter Identification Mechanism
cs.LG, stat.ML
Submitted: 2026-09-01
Updated: 2026-09-01
Code: https://github.com/karpathy/nan
Terminology
Sources
- GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints
- On the Optimization of Deep Networks: Implicit Acceleration by Overparameterization
- Low-Rank Bottleneck in Multi-head Attention Models
- The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks
- Formal Algorithms for Transformers
- RoFormer: Enhanced Transformer with Rotary Position Embedding
- Attention Is All You Need
- Length Generalization of Causal Transformers without Position Encoding
- Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion
- Symmetry in Neural Network Parameter Spaces
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