Cover Image

A Unified Perspective on the Dynamics of Deep Transformers

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Castin, Valérie, Ablin, Pierre, Carrillo, José Antonio, Peyré, Gabriel
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Analysis of PDEs 35Q68 (Primary) 68T07, 35B40 (Secondary)
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Traveling waves of NLS System arising in optical material without Galilean symmetry
by: Li, Yuan, et al.
Published: (2024)

Quantifying Concentration Phenomena of Mean-Field Transformers in the Low-Temperature Regime
by: Alcalde, Albert, et al.
Published: (2026)

Is Stochastic Gradient Descent Effective? A PDE Perspective on Machine Learning processes
by: Barbieri, Davide, et al.
Published: (2025)

Wasserstein-Łojasiewicz inequalities and asymptotics of McKean-Vlasov equation
by: Choi, Beomjun, et al.
Published: (2025)

Large-time behavior of pressureless Euler--Poisson equations with background states
by: Choi, Young-Pil, et al.
Published: (2025)

Stein Variational Gradient Descent dynamics for highly concentrated kernels
by: Carrillo, José A., et al.
Published: (2026)

Variational formulations of ODE-Net as a mean-field optimal control problem and existence results
by: Isobe, Noboru, et al.
Published: (2023)

Neural Shape Operator Surrogates -- Expression Rate Bounds
by: Harbrecht, Helmut, et al.
Published: (2026)

Quantitative Local Convergence of Mean-Field Stein Variational Gradient Flow
by: Chizat, Lénaïc, et al.
Published: (2026)

Neural Discovery of Strichartz Extremizers
by: Valenzuela, Nicolás, et al.
Published: (2026)

SympFormer: Accelerated attention blocks via Inertial Dynamics on Density Manifolds
by: Stein, Viktor, et al.
Published: (2026)

Perturbation Analysis and Neural Network-Based Initial Condition Estimation for the Sine-Gordon Equation
by: Ha, Junhong, et al.
Published: (2025)

On the convergence of PINNs for inverse source problem in the complex Ginzburg-Landau equation
by: Cheng, Xing, et al.
Published: (2025)

Long time decay and asymptotics for the complex mKdV equation
by: Stewart, Gavin
Published: (2021)

Probabilistic Strichartz estimates in Schatten classes and their applications to the Hartree equation
by: Hadama, Sonae, et al.
Published: (2023)

Quantitative analysis for $L^2$-estimates in linear elliptic equations via divergence-free transformation
by: Lee, Haesung
Published: (2025)

Schauder-type estimates and applications
by: Kichenassamy, Satyanad
Published: (2025)

Asymptotic stability of a wide class of stationary solutions for the Hartree and Schrödinger equations for infinitely many particles
by: Hadama, Sonae
Published: (2023)

Rotating solutions to the incompressible Euler-Poisson equation with external particle
by: Alonso-Orán, Diego, et al.
Published: (2023)

Scattering problem for the generalized Korteweg-de Vries equation
by: Masaki, Satoshi, et al.
Published: (2024)

Sharp asymptotic behavior of solutions to damped nonlinear Schrödinger equations
by: Takagi, Kodai, et al.
Published: (2026)

Balanced LoRA: Removing Parameter Invariance to Accelerate Convergence
by: Castin, Valérie, et al.
Published: (2026)

Lyapunov stability and exponential phase-locking of Schrödinger-Lohe quantum oscillators
by: Antonelli, Paolo, et al.
Published: (2024)

Exponential decay of the linear Maxwell system due to conductivity near the boundary
by: Nutt, Richard, et al.
Published: (2026)

A convergence result of a continuous model of deep learning via Łojasiewicz--Simon inequality
by: Isobe, Noboru
Published: (2023)

The Stein-log-Sobolev inequality and the exponential rate of convergence for the continuous Stein variational gradient descent method
by: Carrillo, José A., et al.
Published: (2024)

Incompressible limit for the 3D compressible FENE dumbbell model
by: Gao, Jincheng, et al.
Published: (2025)

Global well-posedness and scattering of the defocusing energy-critical inhomogeneous nonlinear Schrödinger equation with radial data
by: Park, Dongjin
Published: (2023)

Standing waves with prescribed $L^2$-norm to nonlinear Schrödinger equations with combined inhomogeneous nonlinearities
by: Gou, Tianxiang
Published: (2023)

Rigidity of smooth finite-time blow-up for equivariant self-dual Chern-Simons-Schrödinger equation
by: Kim, Kihyun
Published: (2022)

Scattering and localized states for defocusing nonlinear Schrödinger equations with potential
by: Soffer, Avy, et al.
Published: (2024)

Remarks on Linear Growth of Vorticity Gradients and Support Diameters for 2D Euler Flow in Half-Plane
by: Chen, Shaoqing, et al.
Published: (2026)

Near-optimal learning of Banach-valued, high-dimensional functions via deep neural networks
by: Adcock, Ben, et al.
Published: (2022)

A PDE Perspective on Generative Diffusion Models
by: Liu, Kang, et al.
Published: (2025)

Two-Time-Scale Learning Dynamics: A Population View of Neural Network Training
by: Borghi, Giacomo, et al.
Published: (2026)

Periodic gravity-capillary roll wave solutions to the inclined viscous shallow water equations in two dimensions
by: Stevenson, Noah
Published: (2024)

A note on the non-$L^1$ asymptotic completeness of the Vlasov-Maxwell system
by: Breton, Emile
Published: (2025)

Modified scattering for small data solutions to the Vlasov-Maxwell system: a short proof
by: Breton, Emile
Published: (2025)

Existence of multisoliton solutions of the gravitational Hartree equation in three dimensions
by: Wu, Yutong
Published: (2024)

Quantitative Convergence of Wasserstein Gradient Flows of Kernel Mean Discrepancies
by: Chizat, Lénaïc, et al.
Published: (2026)