Linear Algebra Foundations of Efficient Attention: A Phase Reversal in Rank Collapse Under SVD Compression

arXiv:2609.06341 · cs.LG, cs.AI, cs.NE · Submitted 2026-09-06 · Read on arXiv

cs.LG, cs.AI, cs.NE

Submitted: 2026-09-06

Updated: 2026-09-06

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

Terminology

• Calibration — 1× in this paper · explained in 7 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Singular Value Decomposition (SVD) — 1× in this paper · explained in 2 episodes
• Transformer — 1× in this paper · explained in 2 episodes

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