Provably Learning Multi-Head Attention with Queries

arXiv:2608.03294 · cs.LG, cs.CR · Submitted 2026-08-24 · Read on arXiv

Sunyeop Kim, Insung Kim

cs.LG, cs.CR

Submitted: 2026-08-24

Updated: 2026-08-25

Comments: 39 pages

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Transformer — 36× in this paper · explained in 2 episodes
• Accuracy — 5× in this paper · explained in 1 episode
• Decode — 2× in this paper · explained in 2 episodes
• Accountability — 1× in this paper · explained in 2 episodes
• Adaptivity — 1× in this paper · explained in 1 episode
• Attention Mechanism — 1× in this paper · explained in 2 episodes
• Fidelity — 1× in this paper · explained in 2 episodes
• Query Complexity — 1× in this paper · explained in 2 episodes
• Transformer Architecture — 1× in this paper · explained in 2 episodes

Sources

• Provably Learning Attention with Queries
• On Identifiability in Transformers

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