Imagen de Portada

The Mean-Field Dynamics of Transformers

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autor principal:	Rigollet, Philippe
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning Mathematical Physics Dynamical Systems Probability
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

A Dynamics-Informed Gaussian Process Framework for 2D Stochastic Navier-Stokes via Quasi-Gaussianity
por: Hamzi, Boumediene, et al.
Publicado: (2025)

Residual connections provably mitigate oversmoothing in graph neural networks
por: Chen, Ziang, et al.
Publicado: (2025)

Quantitative Clustering in Mean-Field Transformer Models
por: Chen, Shi, et al.
Publicado: (2025)

Weak Generative Sampler to Efficiently Sample Invariant Distribution of Stochastic Differential Equation
por: Cai, Zhiqiang, et al.
Publicado: (2024)

Error Estimation in the Mean-Field Limit of Kinetic Flocking Models with Local Alignments
por: Wang, Jinhuan, et al.
Publicado: (2024)

Mesoscopic and Macroscopic Entropy Balance Equations in a Stochastic Dynamics and Its Deterministic Limit
por: Qian, Hong, et al.
Publicado: (2024)

Mean field limits of particle-based stochastic reaction-drift-diffusion models
por: Heldman, Max, et al.
Publicado: (2023)

Ensemble forecasts in reproducing kernel Hilbert space family
por: Dufée, Benjamin, et al.
Publicado: (2022)

Freezing Phase Transitions for Lattice Systems and Higher-Dimensional Subshifts
por: Chazottes, J. -R., et al.
Publicado: (2025)

Localization of interacting random particles with power-law long-range hopping
por: Jian, Wenwen, et al.
Publicado: (2025)

Notes on SU(2) invariant absolutely continuous probability measures
por: Vitillaro, Giuseppe
Publicado: (2025)

The Eigenfunctions of the Transfer Operator for the Dyson model in a field
por: Makhmudov, Mirmukhsin
Publicado: (2025)

New probabilistic methods for physics
por: Cirier, Guy
Publicado: (2025)

Ergodicity and asymptotic limits for Langevin interacting systems with singular forces and multiplicative noises
por: Duong, Manh Hong, et al.
Publicado: (2026)

The intertwining property for Laguerre processes with a fixed parameter
por: Bufetov, Alexander I., et al.
Publicado: (2024)

Soliton decomposition of the Box-Ball System
por: Ferrari, Pablo A., et al.
Publicado: (2018)

Finitary coding and Gaussian concentration for random fields
por: Chazottes, J. -R., et al.
Publicado: (2026)

Effective quenched linear response for random dynamical systems
por: Dragicevic, Davor, et al.
Publicado: (2024)

Back to Boundaries in Billiards
por: Bunimovich, Leonid, et al.
Publicado: (2022)

Learning Nonholonomic Dynamics with Constraint Discovery
por: Wang, Baiyue, et al.
Publicado: (2024)

A mathematical perspective on Transformers
por: Geshkovski, Borjan, et al.
Publicado: (2023)

Sparse reconstruction in spin systems II: Ising and other factor of IID measures
por: Galicza, Pál, et al.
Publicado: (2024)

Characterizing Dynamical Stability of Stochastic Gradient Descent in Overparameterized Learning
por: Chemnitz, Dennis, et al.
Publicado: (2024)

A Score Filter Enhanced Data Assimilation Framework for Data-Driven Dynamical Systems
por: Tang, Jingqiao, et al.
Publicado: (2026)

Dynamic metastability in the self-attention model
por: Geshkovski, Borjan, et al.
Publicado: (2024)

Homogenized Transformers
por: Koubbi, Hugo, et al.
Publicado: (2026)

Space-Time Statistical Solutions of the Incompressible Euler Equations and Landau-Lifshitz Fluctuating Hydrodynamics
por: Eyink, Gregory L., et al.
Publicado: (2024)

On localization for the alloy-type Anderson-Bernoulli model with long-range hopping
por: Liu, Shihe, et al.
Publicado: (2025)

Analyticity of the pressure function for products of matrices
por: Hautecœur, Arnaud
Publicado: (2025)

Phase transitions for interacting particle systems on random graphs
por: Bertoli, Benedetta, et al.
Publicado: (2025)

Extended states for the Random Schrödinger operator on $\mathbb{Z}^d$ ($d\geq 5$) with decaying Bernoulli potential
por: Liu, Shihe, et al.
Publicado: (2025)

Irregular traces of multiple SLE(0) systems with multiple marked points
por: Zhang, Jiaxin
Publicado: (2025)

Harmonic analysis of multiplicative chaos Part II: a unified approach to Fourier dimensions
por: Lin, Zhaofeng, et al.
Publicado: (2025)

Harmonic analysis of multiplicative chaos Part I: the proof of Garban-Vargas conjecture for 1D GMC
por: Lin, Zhaofeng, et al.
Publicado: (2024)

What is a Fluctuation Theorem?
por: Cuneo, Noé, et al.
Publicado: (2026)

Asymptotic estimates of large gaps between directions in certain planar quasicrystals
por: Hammarhjelm, Gustav, et al.
Publicado: (2024)

Koopman Theory-Inspired Method for Learning Time Advancement Operators in Unstable Flame Front Evolution
por: Yu, Rixin, et al.
Publicado: (2024)

Effective Velocities in the Toda Lattice
por: Aggarwal, Amol
Publicado: (2025)

Interpretation of generalized Langevin equations
por: Sabin-Miller, David, et al.
Publicado: (2022)

Divergence-kernel method for linear responses of densities and generative models
por: Ni, Angxiu
Publicado: (2025)