English
Related papers

Related papers: Quantitative Clustering in Mean-Field Transformer …

200 papers

We develop a mathematical framework that interprets Transformer attention as an interacting particle system and studies its continuum (mean-field) limits. By idealizing attention on the sphere, we connect Transformer dynamics to Wasserstein…

Machine Learning · Computer Science 2026-02-02 Philippe Rigollet

In this paper, we study the evolution of tokens through the depth of encoder-only transformer models at inference time by modeling them as a system of particles interacting in a mean-field way and studying the corresponding dynamics. More…

Machine Learning · Computer Science 2025-09-30 Giuseppe Bruno , Federico Pasqualotto , Andrea Agazzi

We model the evolution of tokens within a deep stack of Transformer layers as a continuous-time flow on the unit sphere, governed by a mean-field interacting particle system, building on the framework introduced in (Geshkovski et al.,…

Machine Learning · Computer Science 2025-04-17 Giuseppe Bruno , Federico Pasqualotto , Andrea Agazzi

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

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

We study a network of finitely many interacting clusters where each cluster is a collection of globally coupled circle maps in the thermodynamic (or mean field) limit. The state of each cluster is described by a probability measure, and its…

Dynamical Systems · Mathematics 2022-09-07 Fanni M. Sélley , Matteo Tanzi

We consider mean-field models for data--clustering problems starting from a generalization of the bounded confidence model for opinion dynamics. The microscopic model includes information on the position as well as on additional features of…

Numerical Analysis · Mathematics 2020-03-16 Michael Herty , Lorenzo Pareschi , Giuseppe Visconti

Transformers are extremely successful machine learning models whose mathematical properties remain poorly understood. Here, we rigorously characterize the behavior of transformers with hardmax self-attention and normalization sublayers as…

Computation and Language · Computer Science 2026-05-14 Albert Alcalde , Giovanni Fantuzzi , Enrique Zuazua

The emergence of explosive synchronization has been reported as an abrupt transition in complex networks of first-order Kuramoto oscillators. In this Letter, we demonstrate that the nodes in a second-order Kuramoto model, perform a cascade…

Adaptation and Self-Organizing Systems · Physics 2015-06-15 Peng Ji , Thomas K. DM. Peron , Peter J. Menck , Francisco A. Rodrigues , Jürgen Kurths

This paper studies a mean field game formulation of the classical Kuramoto model for synchronization. Our model captures the diversity within the population by considering random intrinsic frequencies, which allows us to study the impact of…

Functional Analysis · Mathematics 2025-09-23 Rene Carmona , Quentin Cormier , Mete Soner

This paper investigates the use of transformers to approximate the mean-field dynamics of interacting particle systems exhibiting collective behavior. Such systems are fundamental in modeling phenomena across physics, biology, and…

Computational Physics · Physics 2025-05-29 Shiba Biswal , Karthik Elamvazhuthi , Rishi Sonthalia

A striking clustering phenomenon in the antiferromagnetic Hamiltonian Mean-Field model has been previously reported. The numerically observed bicluster formation and stabilization is here fully explained by a non linear analysis of the…

Statistical Mechanics · Physics 2009-11-07 Julien Barre , Thierry Dauxois , Stefano Ruffo

The cluster synchronization is a very important characteristic for the higher harmonic coupling Kuramoto system. A novel transformation is provided, and it gives cluster synchronization by the periodic properties of the density function.…

Chaotic Dynamics · Physics 2015-11-05 Guihua Tian , Songhua Hu , Shuquan Zhong

This paper considers a mean-field model of $n$ interacting particles whose state space is the unit circle, a generalization of the classical Kuramoto model. Global synchronization is said to occur if after starting from almost any initial…

Dynamical Systems · Mathematics 2025-07-31 Yury Polyanskiy , Philippe Rigollet , Andrew Yao

We develop, clarify and test various aspects of cluster methods dynamical mean field methods using a soluble toy model as a benchmark. We find that the Cellular Dynamical Mean Field Theory (C-DMFT) converges very rapidly and compare its…

Strongly Correlated Electrons · Physics 2009-11-07 Giulio Biroli , Gabriel Kotliar

The Kuramoto model, despite its popularity as a mean-field theory for many synchronization phenomenon of oscillatory systems, is limited to a first-order harmonic coupling of phases. For higher-order coupling, there only exists a…

Adaptation and Self-Organizing Systems · Physics 2020-01-22 Chen Chris Gong , Arkady Pikovsky

The extended dynamical mean field theory has played an important role in the study of quantum phase transitions in heavy fermion systems. In order to incorporate the physics of unconventional superconductivity, we develop a cluster version…

Strongly Correlated Electrons · Physics 2015-05-19 J. H. Pixley , Ang Cai , Qimiao Si

Quantum cluster approaches offer new perspectives to study the complexities of macroscopic correlated fermion systems. These approaches can be understood as generalized mean-field theories. Quantum cluster approaches are non-perturbative…

Strongly Correlated Electrons · Physics 2009-11-10 Th. Maier , M. Jarrell , Th. Pruschke , M. H. Hettler

A general expansion scheme based on the concept of linked cluster expansion from the theory of classical spin systems is constructed for models of interacting electrons. It is shown that with a suitable variational formulation of mean-field…

Condensed Matter · Physics 2009-10-28 Vaclav Janis , Jan Schlipf

Simulations of extended quantum systems are typically performed by extrapolating results of a sequence of finite-system-size simulations to the thermodynamic limit. In the quantum Monte Carlo community, twist-averaging was pioneered as an…

Strongly Correlated Electrons · Physics 2022-12-14 Sergei Iskakov , Hanna Terletska , Emanuel Gull
‹ Prev 1 2 3 10 Next ›