cs.LGMay 29, 2026

Reachability and asymptotics of Gaussian Transformer dynamics

Authors: Albert AlcaldeZhengping JiEnrique Zuazua

Organizations: †Chair for Dynamics, Control, Machine Learning & Numerics (Alexander von Humboldt Profes- sorship), Department of Mathematics, Friedrich–Alexander-Universität Erlangen–Nürnberg, 91058 Erlangen, Germany. · ‡Departamento de Matem´aticas, Universidad Aut´onoma de Madrid, 28049 Madrid, Spain. · Chair of Computational Mathematics, Fundaci´on Deusto. Av. de las Universidades, 24, 48007 Bilbao, Basque Country, Spain.

Abstract

We formulate data propagation through the Transformer, the machine learning architecture powering large language models, as a nonlinear control system on the space of probability measures. For the mean-field Transformer model with self-attention and affine feed-forward layers, we prove that Gaussian distributions remain exactly Gaussian along the induced flow. This invariance reduces the infinite-dimensional measure dynamics to a finite-dimensional bilinear control system governing the evolution of the mean and covariance, reformulates the expressive capacity of Transformers as a reachability problem for prescribed Gaussian moments, and reveals a novel connection with Riccati-type equations from classical filtering and control. For time-varying controls, we prove exact finite-time reachability of any target Gaussian distribution whose covariance matrix has the same rank as the initial one, this rank constraint being an intrinsic invariant of the dynamics. For time-invariant parameters, we derive explicit spectral conditions leading either to asymptotic stability toward positive-definite equilibria or to finite-time blow-up of the covariance. Numerical experiments complement the theory by showing that practical Transformers with Gaussian inputs remain close to moment-matched Gaussian distributions through early and intermediate layers, while Transformers with prescribed attention matrices reproduce the predicted covariance regimes: bounded evolution in stabilizing configurations and blow-up in destabilizing ones.

Explore similar work

Jul 30, 2026cs.LG

Generalization Bounds on Optimal Control for Transformer Training and Wasserstein Distributional Robustness

We derive finite-sample generalization bounds for Transformers trained with dynamic programming recursions. Building on the doubly lifted, measure-valued formulation of Transformer dynamics, we view data sets as probability laws on pairs of empirical input-output measures, allowing us to interpret the training problem as a finite-horizon Markovian control problem. We then analyze a quantized model, derived by quantizing the state, action, and measure-state spaces, and derive explicit finite-sample generalization bounds using concentration inequalities for empirical laws on finite metric spaces together with a Lipschitz stability estimate for the value function. These bounds are transferred to the base model at the cost of an explicit approximation error. Finally, we show that the same machinery yields a distributionally robust control formulation of the training problem, connecting Transformer generalization to Wasserstein distributionally robust optimization.
Kağan Akman, Naci Saldi, Serdar Yüksel
May 11, 2026math.AP

Quantifying Concentration Phenomena of Mean-Field Transformers in the Low-Temperature Regime

Transformers with self-attention modules as their core components have become an integral architecture in modern large language and foundation models. In this paper, we study the evolution of tokens in deep encoder-only transformers at inference time which is described in the large-token limit by a mean-field continuity equation. Leveraging ideas from the convergence analysis of interacting multi-particle systems, with particles corresponding to tokens, we prove that the token distribution rapidly concentrates onto the push-forward of the initial distribution under a projection map induced by the key, query, and value matrices, and remains metastable for moderate times. Specifically, we show that the Wasserstein distance of the two distributions scales like log(β+1)/βexp(Ct)+exp(ct)\sqrt{{\log(β+1)}/β}\exp(Ct)+\exp(-ct) in terms of the temperature parameter β10β^{-1}\to 0 and inference time t0t\geq 0. For the proof, we establish Lyapunov-type estimates for the zero-temperature equation, identify its limit as tt\to\infty, and employ a stability estimate in Wasserstein space together with a quantitative Laplace principle to couple the two equations. Our result implies that for time scales of order logβ\logβ the token distribution concentrates at the identified limiting distribution. Numerical experiments confirm this and, beyond that, complement our theory by showing that for finite ββ and large tt the dynamics enter a different terminal phase, dominated by the spectrum of the value matrix.
Albert Alcalde, Leon Bungert, Konstantin Riedl +1
May 16, 2026cs.LG

Propagation of Chaos in Contextual Flow Maps

We develop a quantitative statistical theory of transformers in the large-context regime by adopting the abstraction of contextual flow maps (CFMs): dynamical systems that evolve a distinguished token in the presence of a contextual measure across a stack of attention blocks. Within this framework, the finite-context model approximates an idealized infinite-context system in which the contextual measure is replaced by its underlying population, so that the context length nn becomes a statistical resource. Exploiting the McKean--Vlasov structure of the dynamics and the classical machinery of propagation of chaos, we establish a forward bound controlling the deviation between the finite- and infinite-context CFMs uniformly along depth, and a backward bound controlling the deviation between the corresponding training trajectories uniformly across iterations of online gradient descent. Both bounds achieve the optimal Wasserstein rate n1/dn^{-1/d} for general CFMs and parametric rate n1/2n^{-1/2} for a restricted class of CFMs that includes transformers as a special case. The analysis rests on a new Eulerian adjoint formulation of the loss gradient and stability estimates for the resulting forward--adjoint system, both of which may be of independent interest.
Shi Chen, Zhengjiang Lin, Kaizhao Liu +1