Cover Image

Kinetic theory for Transformers and the lost-in-the-middle phenomenon

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Duerinckx, Mitia, Geshkovski, Borjan, Rossi, Stefano
Format:	Preprint
Published:	2026
Subjects:	Analysis of PDEs Machine Learning Probability
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Constructive conditional normalizing flows
by: Geshkovski, Borjan, et al.
Published: (2026)

Homogenization of the stochastic double-porosity model
by: Bonhomme, Elise, et al.
Published: (2025)

Singular mean-field limits for fluctuations around equilibrium
by: Duerinckx, Mitia, et al.
Published: (2026)

Correlation estimates for Brownian particles with singular interactions
by: Duerinckx, Mitia, et al.
Published: (2025)

Creation of chaos for interacting Brownian particles
by: Bernou, Armand, et al.
Published: (2025)

On Bourgain's approach to stochastic homogenization
by: Duerinckx, Mitia, et al.
Published: (2024)

A mathematical perspective on Transformers
by: Geshkovski, Borjan, et al.
Published: (2023)

The emergence of clusters in self-attention dynamics
by: Geshkovski, Borjan, et al.
Published: (2023)

Homogenized Transformers
by: Koubbi, Hugo, et al.
Published: (2026)

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

Homogenization of the 2D Euler system: lakes and porous media
by: Duerinckx, Mitia, et al.
Published: (2024)

A transport approach to the cutoff phenomenon
by: Pedrotti, Francesco, et al.
Published: (2025)

Mean-field approximation, Gibbs relaxation, and cross estimates
by: Bernou, Armand, et al.
Published: (2025)

Dynamics of point-vortex type systems near thermal equilibrium: relaxation or not?
by: Duerinckx, Mitia, et al.
Published: (2024)

Lenard-Balescu thermalization: rigorous derivation from a toy model
by: Duerinckx, Mitia, et al.
Published: (2025)

Uniform-in-time estimates on corrections to mean field for interacting Brownian particles
by: Bernou, Armand, et al.
Published: (2024)

Neural Sampling from Boltzmann Densities: Fisher-Rao Curves in the Wasserstein Geometry
by: Chemseddine, Jannis, et al.
Published: (2024)

Independent projections of diffusions: Gradient flows for variational inference and optimal mean field approximations
by: Lacker, Daniel
Published: (2023)

Birth-death dynamics for sampling: Global convergence, approximations and their asymptotics
by: Lu, Yulong, et al.
Published: (2022)

A duality method for mean-field limits with singular interactions
by: Bresch, Didier, et al.
Published: (2024)

The superposition principle for the continuity equation with singular flux
by: Almi, Stefano, et al.
Published: (2025)

Space-time deep neural network approximations for high-dimensional partial differential equations
by: Hornung, Fabian, et al.
Published: (2020)

Hydrodynamic limit of multiscale viscoelastic models for rigid particle suspensions
by: Duerinckx, Mitia, et al.
Published: (2023)

One model to solve them all: 2BSDE families via neural operators
by: Furuya, Takashi, et al.
Published: (2025)

From Monte Carlo to neural networks approximations of boundary value problems
by: Beznea, Lucian, et al.
Published: (2022)

Large-scale dispersive estimates for acoustic operators: homogenization meets localization
by: Duerinckx, Mitia, et al.
Published: (2023)

Game theoretical asymptotic mean value properties for non-homogeneous $p$-Laplace problems
by: del Teso, Félix, et al.
Published: (2024)

Singular jump processes as generalized gradient flows
by: Hoeksema, Jasper, et al.
Published: (2025)

Kinetic Theory with Fluctuations: Strong Well-Posedness of the Vlasov-Fokker-Planck-Dean-Kawasaki System
by: Hao, Zimo, et al.
Published: (2025)

Systems involving mean value formulas on trees
by: Miranda, Alfredo, et al.
Published: (2021)

On Heat kernel Estimtes for Brownian SDEs with Distributional Drift
by: Menozzi, Stéphane, et al.
Published: (2026)

A new spectral analysis of stationary random Schrödinger operators
by: Duerinckx, Mitia, et al.
Published: (2020)

A game-theoretical interpretation for a doubly nonlinear parabolic equation
by: del Teso, Felix, et al.
Published: (2026)

Approximation of symmetric total variation on point clouds
by: Almi, Stefano, et al.
Published: (2026)

Some properties on the reversibility and the linear response theory of Langevin dynamics
by: Gao, Yuan, et al.
Published: (2024)

Regularization of the superposition principle: Potential theory meets Fokker-Planck equations
by: Beznea, Lucian, et al.
Published: (2026)

Krylov-Safonov theory for Pucci-type extremal inequalities on random data clouds
by: Arroyo, Ángel, et al.
Published: (2024)

Propagation of Chaos in Contextual Flow Maps
by: Chen, Shi, et al.
Published: (2026)

A new approach for the unitary Dyson Brownian motion through the theory of viscosity solutions
by: Bertucci, Charles, et al.
Published: (2025)

Non-local Boundary Value Problems, stochastic resetting and Brownian motions on graphs
by: Bonaccorsi, Stefano, et al.
Published: (2022)