On the Structure of Stationary Solutions to McKean-Vlasov Equations with Applications to Noisy Transformers
Not on the map. Why?
Abstract (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-dimensional quadratic system of equations over Fourier coefficients, which allows explicit characterization of the stationary states in a sequence space rather than a function space. This framework provides a transparent description of local bifurcations, characterizing their periodicity, and resonance structures, while accommodating singular potentials. We derive analytic expressions that characterize the emergence, form and shape (supercritical, critical, subcritical or transcritical) of bifurcations involving possibly multiple Fourier modes and connect them with discontinuous phase transitions. We also characterize, under suitable assumptions, the detailed structure of the stationary bifurcating solutions that are accurate upto an arbitrary number of Fourier modes. At the global level, we establish regularity and concavity properties of the free energy landscape, proving existence, compactness, and coexistence of globally minimizing stationary measures, further identifying discontinuous phase transitions with points of non-differentiability of the minimum free energy map. As an application, we specialize the theory to the Noisy Mean-Field Transformer model, where we show how changing the inverse temperature parameter β affects the geometry of the infinitely many bifurcations from the uniform measure. We also explain how increasing β can lead to a rich class of approximate multi-mode stationary solutions which can be seen as `metastable states'. Further, a sharp transition from continuous to discontinuous (first-order) phase behavior is observed as β increases.
Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 7 of its 38 references that are in the map. First posted on arXiv 23 Oct 2025.
Builds on
7 of 38 references.
References · 7
- 2023A mathematical perspective on Transformerscited by 160
- 2024Dynamic metastability in the self-attention modelcited by 42
- 2024Emergence of meta-stable clustering in mean-field transformer modelscited by 35
- 2024Clustering in Causal Attention Maskingcited by 31
- 2025A Unified Perspective on the Dynamics of Deep Transformerscited by 30
- 2025A multiscale analysis of mean-field transformers in the moderate interaction regimecited by 24
- 2025Quantitative Clustering in Mean-Field Transformer Modelscited by 23
Built on by
Citing papers per year: 2025: 1; 2026: 9.
10 papers.
- 2025The Mean-Field Dynamics of Transformerscited by 24
- 2026Perceptrons and localization of attention's mean-field landscapecited by 7
- 2026Clustering in Deep Stochastic Transformerscited by 5
- 2026Quantifying Concentration Phenomena of Mean-Field Transformers in the Low-Temperature Regimecited by 4
- 2026Phase transitions in Doi-Onsager, Noisy Transformer, and other multimodal modelscited by 1
- 2026Training-Induced Escape from Token Clustering in a Mean-Field Formulation of Transformerscited by 1
- 2026L2 over Wasserstein: Statistical Analysis for Optimal Transportcited by 1
- 2026Multi-Headed Transformer Architectures as Time-dependent Wasserstein Gradient Flowscited by 0
- 2026Phase transitions for the noisy transformer model in arbitrary dimensioncited by 0
- 2026Random Quadratic Form with random forcing: Metastable synchronization by noisecited by 0
- 2026Random Quadratic Form with random forcing: Metastable synchronization by noise17 Aug 2026
- 2026Phase transitions for the noisy transformer model in arbitrary dimension3 Jun 2026
- 2026L2 over Wasserstein: Statistical Analysis for Optimal Transport20 May 2026
- 2026Multi-Headed Transformer Architectures as Time-dependent Wasserstein Gradient Flows15 May 2026
- 2026Quantifying Concentration Phenomena of Mean-Field Transformers in the Low-Temperature Regime11 May 2026
- 2026Training-Induced Escape from Token Clustering in a Mean-Field Formulation of Transformers8 May 2026
- 2026Phase transitions in Doi-Onsager, Noisy Transformer, and other multimodal models17 Apr 2026
- 2026Clustering in Deep Stochastic Transformers29 Jan 2026
- 2026Perceptrons and localization of attention's mean-field landscape29 Jan 2026
- 2025The Mean-Field Dynamics of Transformers1 Dec 2025