Relevant and Irrelevant: A Renormalization Group Analysis of Transformer Attention

• URL: http://arxiv.org/abs/2607.15449v1
• Date: Thu, 16 Jul 2026 20:42:02 GMT
• Title: Relevant and Irrelevant: A Renormalization Group Analysis of Transformer Attention
• Abstract summary: We treat the Transformer's attention mechanism as a perturbation of the trained residual-stack fixed point.<n>Testable predictions are made for the fixed-point geometry, effective rank profile, layer specificity, and perturbation decay spectrum.
• Score: 16.36212521143563
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Using the language of Wilsonian renormalization group theory (RG), we treat the Transformer's attention mechanism as a perturbation of the trained MLP residual-stack fixed point and ask whether it constitutes a relevant, marginal, or irrelevant operator. We derive a fixed-point shift formula and obtain four testable predictions for the fixed-point geometry, effective rank profile, layer specificity, and perturbation decay spectrum. Testing these on synthetic Markov chain sequences with controlled correlation length, we find: (1) For large chains(long correlation), attention is strongly relevant: it closes a residual loss gap the MLP cannot bridge and drives a phase transition in representation space, with effective rank jumping above input dimensionality at layer 1 and stabilizing at a high-dimensional plateau. (2) For short chains(short correlation), attention is irrelevant: the Transformer converges to the same loss and fixed-point geometry as the MLP, though it contracts perturbations faster. (3) The transition is dominated by the first-layer head (L0H0), which accounts for more than 4 times the representational shift of any subsequent head, consistent with the prediction that the relevant operator acts before the MLP begins integrating out positional variation. (4) Perturbation decay experiments reveal a regime reversal: in the long correlation regime the Transformer selectively preserves slow Markov modes (5.4 times the dynamic range in decay length vs. 1.3 times for the MLP); in the short correlation regime it suppresses all modes faster than the MLP, with no spectral selectivity. Together, these results show that the relevance of attention is not a property of the architecture but of the spectral structure of the data-generating process, and that a first-order RG perturbation framework provides a predictive account of that difference.

Related papers

• From Concentration to Differentiation and Back: Routing Effective Rank in MoE Reasoning Cohorts [61.695980784491475]
  Test-time scaling produces cohorts of reasoning rollouts, yet there is no standard label-free account of how their internal computation reorganizes as inference unfolds.<n>We introduce routing effective rank deff, the entropy-effective dimensionality of a cross-rollout graph built from MoE expert-routing similarity.
  arXiv  Detail & Related papers  (2026-09-06T05:43:22Z)
• Beyond Tokens: Probing Higher-Order Epistasis in Learned Protein Representations [3.1035948531044912]
  We introduce ORBIT, an Order-Resolved Benchmarking of Interaction Transformations framework that separates interaction presence, representation accessibility, and functional recovery.<n>We compare ridge regression, a standard, independent tokens, nonlinear independent tokens, and Residual Interaction Tokenization (RIT)<n>RIT significantly increased pairwise accessibility at the token stage relative to both independent-token controls.
  arXiv  Detail & Related papers  (2026-08-24T23:35:36Z)
• Rank Collapse, Fixed Points, and the Renormalization Group Structure of MLP Residual Networks [16.36212521143563]
  We study the simplest architecture for which the analogy is tractable.<n>The effective rank of the residual stream decreases monotonically with depth after training.<n>The network preserves exactly the degrees of freedom relevant to the prediction task.
  arXiv  Detail & Related papers  (2026-06-09T02:19:26Z)
• Unified Geometry-Guided ML-FTLE for Tracking Transient Chaos from Scalar Time Series [0.0]
  We propose a geometry-guided machine learning framework that unifies predictive trajectory divergence with macroscopic attractor morphology to track abrupt regime shifts.<n>This equation-free framework provides a highly accurate, noise-resilient diagnostic for monitoring structural transitions in complex non-stationary systems.
  arXiv  Detail & Related papers  (2026-06-05T15:22:57Z)
• Contrast to Detect: Dynamic Graph Contrastive Regularization for Unsupervised Anomaly Detection in Multivariate Time Series [24.192601578775186]
  We propose ContrastAD, an unsupervised framework that turns structural evolution into a learning signal rather than suppressing it.<n>Across five real-world benchmarks, ContrastAD attains the highest mean F1 and the highest AUC on three datasets.
  arXiv  Detail & Related papers  (2026-05-22T15:18:53Z)
• A Systematic Empirical Study of Grokking: Depth, Architecture, Activation, and Regularization [0.0]
  Grokking the delayed transition from memorization to generalization in neural networks remains poorly understood.<n>We present a controlled study that systematically disentangles factors on modular addition (mod 97)<n>Our central finding is that grokking dynamics are not primarily determined by architecture, but by interactions between stability and regularization.
  arXiv  Detail & Related papers  (2026-03-26T04:16:01Z)
• Shift Before You Learn: Enabling Low-Rank Representations in Reinforcement Learning [56.87989363424]
  We show that a low-rank structure naturally emerges in the shifted successor measure.<n>We quantify the amount of shift needed for effective low-rank approximation and estimation.
  arXiv  Detail & Related papers  (2025-09-05T15:48:20Z)
• Provable In-Context Learning of Nonlinear Regression with Transformers [66.99048542127768]
  In-context learning (ICL) is the ability to perform unseen tasks using task specific prompts without updating parameters.<n>Recent research has actively explored the training dynamics behind ICL, with much of the focus on relatively simple tasks.<n>This paper investigates more complex nonlinear regression tasks, aiming to uncover how transformers acquire in-context learning capabilities.
  arXiv  Detail & Related papers  (2025-07-28T00:09:28Z)
• Implicit Bias and Fast Convergence Rates for Self-attention [26.766649949420746]
  We study the fundamental optimization principles of self-attention, the defining mechanism of transformers.<n>We analyze the implicit bias of gradient-baseds in a self-attention layer with a decoder in a linear classification.
  arXiv  Detail & Related papers  (2024-02-08T15:15:09Z)
• Transformers as Support Vector Machines [54.642793677472724]
  We establish a formal equivalence between the optimization geometry of self-attention and a hard-margin SVM problem. We characterize the implicit bias of 1-layer transformers optimized with gradient descent. We believe these findings inspire the interpretation of transformers as a hierarchy of SVMs that separates and selects optimal tokens.
  arXiv  Detail & Related papers  (2023-08-31T17:57:50Z)
• Unraveling Attention via Convex Duality: Analysis and Interpretations of Vision Transformers [52.468311268601056]
  This paper analyzes attention through the lens of convex duality. We derive equivalent finite-dimensional convex problems that are interpretable and solvable to global optimality. We show how self-attention networks implicitly cluster the tokens, based on their latent similarity.
  arXiv  Detail & Related papers  (2022-05-17T04:01:15Z)
• Pruning Redundant Mappings in Transformer Models via Spectral-Normalized Identity Prior [54.629850694790036]
  spectral-normalized identity priors (SNIP) is a structured pruning approach that penalizes an entire residual module in a Transformer model toward an identity mapping. We conduct experiments with BERT on 5 GLUE benchmark tasks to demonstrate that SNIP achieves effective pruning results while maintaining comparable performance.
  arXiv  Detail & Related papers  (2020-10-05T05:40:56Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.