Paper

Rank Collapse, Fixed Points, and the Renormalization Group Structure of MLP Residual Networks

Unreadunread

AI summary

arXiv:2606. 10324v1 Announce Type: cross Abstract: The analogy between deep neural network forward passes and renormalization group (RG) flows has been repeatedly noted in the literature, but existing treatments remain qualitative: depth is described as a coarse-graining scale, attention is likened to a partition function, and representations are said to flow toward fixed points.

Reading status

Priority

About this paper

Authors: Parviz Haggi-Mani, Irina Rish
Released: 2026-06-10 (29d ago)
Topic: Related to current project
Relation to my work: Read next because Rank Collapse, Fixed Points, and the Renormalization Group Structure of MLP Residual Networks overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion language into bystander directives the model was never trained on, absent under same-language SFT (LOW confidence)", clean result "A pretraining-data-poisoned Qwen3-4B backdoor only fires on the exact trigger tokens — paraphrases don't activate it, and base-model similarity to the trigger doesn't predict which inputs fire (MODERATE confidence)", clean result "The marker is a representational handle, not a behavioural one — sharing it between a villain persona and the assistant transfers no misalignment (HIGH confidence)". Matching terms: under, token, rate, implement, control, chain, trained, length. Source: arxiv stat.ML (Machine Learning).
arXiv: 2606.10324

Ask Claude about this paper

Posts a comment with @claude so the runner spins up a Claude Code session scoped to Rank Collapse, Fixed Points, and the Renormalization Group Structure of MLP Residual Networks. Replies appear in the conversation below.

Comments

No comments yet.

Related records

No links yet.