English
Related papers

Related papers: Homogenized Transformers

200 papers

Systems with conserved currents driven by reservoirs at the boundaries offer an opportunity for a general analytic study that is unparalleled in more general out of equilibrium systems. The evolution of coarse-grained variables is governed…

Statistical Mechanics · Physics 2008-11-14 Julien Tailleur , Jorge Kurchan , Vivien Lecomte

While modern representation learning relies heavily on global error signals, decentralized algorithms driven by local interactions offer a fundamental distributed alternative. However, the macroscopic convergence properties of these…

Machine Learning · Computer Science 2026-04-21 Zilin Li , Weiwei Xu , Xuchun Tong , Xuanbo Lu , Xuanqi Zhao

Dynamic heterogeneity has often been modeled by assuming that a single-particle observable, fluctuating at a molecular scale, is influenced by its coupling to environmental variables fluctuating on a second, perhaps slower, time scale.…

Condensed Matter · Physics 2009-11-07 Gregor Diezemann , Gerald Hinze , Hans Sillescu

We show that a constant number of self-attention layers can efficiently simulate, and be simulated by, a constant number of communication rounds of Massively Parallel Computation. As a consequence, we show that logarithmic depth is…

Machine Learning · Computer Science 2024-02-15 Clayton Sanford , Daniel Hsu , Matus Telgarsky

We present a first-principles formalism for studying dynamical heterogeneities in glass forming liquids. Based on the Non-Equilibrium Self-Consistent Generalized Langevin Equation theory, we were able to describe the time-dependent local…

Soft Condensed Matter · Physics 2022-04-06 J. Lira-Escobedo , J. R. Velez-Cordero , Pedro E. Ramírez-González

We study homogenization of a locally periodic two-scale dual-continuum system where each continuum interacts with the other. Equations for each continuum are written separately with interaction terms (exchange terms) added. The…

Numerical Analysis · Mathematics 2019-10-17 Jun Sur Richard Park , Viet Ha Hoang

We consider a one-dimensional diffusion process with coefficients that are periodic outside of a finite 'interface region'. The question investigated in this article is the limiting long time / large scale behaviour of such a process under…

Probability · Mathematics 2010-05-14 Martin Hairer , Charles Manson

In this work, we analyze various scaling limits of the training dynamics of transformer models in the feature learning regime. We identify the set of parameterizations that admit well-defined infinite width and depth limits, allowing the…

Machine Learning · Statistics 2024-10-07 Blake Bordelon , Hamza Tahir Chaudhry , Cengiz Pehlevan

We perform the homogenization process avoiding the necessity of testing the weak formulation of the initial and homogenized systems by corresponding weak solutions. We show that the stress tensor for homogenized problem depends on the…

Analysis of PDEs · Mathematics 2016-08-05 Miroslav Bulíček , Martin Kalousek , Petr Kaplický

We study a model for a dilute suspension of rod-like particles swimming at constant velocity in a Stokes flow. As the translational diffusivity of the particles decreases, a two-dimensional uniform concentration of randomly aligned…

Fluid Dynamics · Physics 2026-05-12 Yves-Marie Ducimetière , Michael J. Shelley

In this paper, we study the homogenization of the distribution-dependent stochastic abstract fluid models by combining the $two\!-\!scale$ convergence and martingale representative approach. A general framework of the homogenization…

Analysis of PDEs · Mathematics 2024-12-20 Junlong Chen , Zhaoyang Qiu , Yanbin Tang

Inspired by topological data analysis techniques, we introduce persistent homology observables and apply them in a geometric analysis of the dynamics of quantum field theories. As a prototype application, we consider data from a…

Quantum Gases · Physics 2021-09-23 Daniel Spitz , Jürgen Berges , Markus K. Oberthaler , Anna Wienhard

Transformers perform inference by iteratively transforming token representations across layers. This layerwise computation has been studied empirically, and recent mean-field theories of Transformer dynamics explain how attention can drive…

Machine Learning · Computer Science 2026-05-11 Noboru Isobe , Daisuke Inoue , Masaaki Imaizumi

We study the effect of normalization schemes on token representations in deep transformers. Modeling their evolution as interacting particles on the sphere, we show that normalization acts as a form of speed regulation. This perspective…

Machine Learning · Computer Science 2025-11-12 Nikita Karagodin , Shu Ge , Yury Polyanskiy , Philippe Rigollet

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…

Analysis of PDEs · Mathematics 2026-05-12 Albert Alcalde , Leon Bungert , Konstantin Riedl , Tim Roith

In this paper, we derive new continuous time limits of the Utterance Selection Model (USM) for language change (Baxter et al., Phys. Rev. E {\bf 73}, 046118, 2006). This is motivated by the fact that the Fokker-Planck continuous time limit…

Physics and Society · Physics 2017-03-08 Jérôme Michaud

In this paper, we study the homogenization of a diffusion process with jumps, that is, Feller process generated by an integro-differential operator. This problem is closely related to the problem of homogenization of boundary value problems…

Probability · Mathematics 2015-11-19 Nikola Sandrić

We develop a classical well-posedness and regularity theory on a finite connected weighted graph for an extended mean field game system, its associated master equation, and a Hamilton-Jacobi- Bellman equation on the probability simplex, all…

Analysis of PDEs · Mathematics 2026-05-08 Wilfrid Gangbo , Sebastian Munoz , Jeremy Wu , Zhaoyu Zhang

Interacting particle systems provide a fundamental framework for modeling collective behavior in biological, social, and physical systems. In many applications, stochastic perturbations are essential for capturing environmental variability…

Adaptation and Self-Organizing Systems · Physics 2026-02-04 Su Yang , Weiqi Chu , Panayotis G. Kevrekidis

We study the problem of homogenization for inertial particles moving in a time dependent random velocity field and subject to molecular diffusion. We show that, under appropriate assumptions on the velocity field, the large--scale,…

Mathematical Physics · Physics 2007-05-23 G. A. Pavliotis , A. M. Stuart , K. C. Zygalakis
‹ Prev 1 3 4 5 6 7 10 Next ›