paper-with-me

홈 › Papers

Phase transitions for the noisy transformer model in arbitrary dimension

2026-06-03 · Kyunghoo Mun, Matthew Rosenzweig arxiv

We study the McKean--Vlasov free energy on the unit sphere associated with the unnormalized self-attention (USA) model for noisy transformer dynamics. We prove a sharp global-minimizer dichotomy in every dimension $d\ge2$. There is a unique $β_*^{(d)}>0$ such that \begin{equation*} \frac{I_{d/2+1}(β_*^{(d)})}{I_{d/2}(β_*^{(d)})}=\frac1d, \end{equation*} where $I_ν$ is the modified Bessel function of the first kind. For $0<β\le β_*^{(d)}$, the uniform density remains the unique global minimizer up to the linear-stability threshold \begin{equation*} K_\#^{(d)}(β)=\frac{β^{d/2}}{2^{d/2}Γ(d/2)I_{d/2}(β)}, \end{equation*} and the phase transition is continuous. For $β>β_*^{(d)}$, the uniform density is not globally minimizing at $K_\#^{(d)}(β)$, so the critical coupling satisfies $K_c<K_\#^{(d)}(β)$ and the transition is discontinuous. This result generalizes the authors' recent $d=2$ work arXiv:2604.16288 to arbitrary dimension. The proof uses the sharp Beckner--Onofri/logarithmic Hardy-Littlewood-Sobolev (HLS) inequality on the sphere, together with a Funk--Hecke/Bessel coefficient computation and a degree-two quartic obstruction.

📄 PDF Abstract BibTeX arXiv:2606.05140

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Phase transitions in Doi-Onsager, Noisy Transformer, and other multimodal models

2026-04-17 · Kyunghoo Mun, Matthew Rosenzweig arxiv

We study phase transitions for repulsive-attractive mean-field free energies on the circle. For a $\frac{1}{n+1}$-periodic interaction whose Fourier coefficients satisfy a certain decay condition, we prove that the criti…

On the Structure of Stationary Solutions to McKean-Vlasov Equations with Applications to Noisy Transformers

2025-10-23 · Krishnakumar Balasubramanian, Sayan Banerjee, Philippe Rigollet arxiv

We study stationary solutions of McKean-Vlasov equations on the circle. Our main contributions stem from observing an exact equivalence between solutions of the stationary McKean-Vlasov equation and an infinite-dimension…

Phase Transitions in Large Language Models and the $O(N)$ Model

2025-01-27 · Youran Sun, Babak Haghighat

Large language models (LLMs) exhibit unprecedentedly rich scaling behaviors. In physics, scaling behavior is closely related to phase transitions, critical phenomena, and field theory. To investigate the phase transition…

Text Generation

0-1 phase transitions in sparse spiked matrix estimation

2019-11-12 · Jean Barbier, Nicolas Macris

We consider statistical models of estimation of a rank-one matrix (the spike) corrupted by an additive gaussian noise matrix in the sparse limit. In this limit the underlying hidden vector (that constructs the rank-one m…

Image RestorationObject CountingSemantic SegmentationWord Sense Disambiguation

Attention to Order: Transformers Discover Phase Transitions via Learnability

2025-10-08 · Şener Özönder arxiv

Phase transitions mark qualitative reorganizations of collective behavior, yet identifying their boundaries remains challenging whenever analytic solutions are absent and conventional simulations fail. Here we introduce …

Self-Supervised Learning