Copertina

Analysis of mean-field models arising from self-attention dynamics in transformer architectures with layer normalization

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Burger, Martin, Kabri, Samira, Korolev, Yury, Roith, Tim, Weigand, Lukas
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Analysis of PDEs 68Q32, 49Q20, 43A35
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Adversarial flows: A gradient flow characterization of adversarial attacks
di: Weigand, Lukas, et al.
Pubblicazione: (2024)

Well-posedness of the transport of normal currents by time-dependent vector fields
di: Bonicatto, Paolo, et al.
Pubblicazione: (2025)

Teaching and Learning under Deductive Errors
di: Telle, Jan Arne, et al.
Pubblicazione: (2026)

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

Monge-Kantorovich Fitting With Sobolev Budgets
di: Kobayashi, Forest, et al.
Pubblicazione: (2024)

Tighter Learning Guarantees on Digital Computers via Concentration of Measure on Finite Spaces
di: Kratsios, Anastasis, et al.
Pubblicazione: (2024)

Linearized dynamic stability for vortices of Ginzburg-Landau evolutions
di: Palacios, José M., et al.
Pubblicazione: (2024)

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

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

A general Frobenius' Theorem via the Transport of Currents
di: Bonicatto, Paolo
Pubblicazione: (2025)

A simple proof of the $1$-dimensional flat chain conjecture
di: Marchese, Andrea, et al.
Pubblicazione: (2024)

Minimally singular functions and the rigidity problem for Steiner's perimeter inequality
di: Perugini, Matteo
Pubblicazione: (2024)

Equivalence of Uniform Polyconvexity and Almgren Uniform Ellipticity for Lipschitz $Q$-Graph Test Pairs
di: Lesniak, Maciej
Pubblicazione: (2026)

No-Regret Generative Modeling via Parabolic Monge-Ampère PDE
di: Deb, Nabarun, et al.
Pubblicazione: (2025)

Initialization-driven neural generation and training for high-dimensional optimal control and first-order mean field games
di: Assouli, Mouhcine, et al.
Pubblicazione: (2025)

Euler's elastica functional as a large mass limit of a two-dimensional non-local isoperimetric problem
di: Muratov, Cyrill B., et al.
Pubblicazione: (2025)

Density of the boundary regular set of 2d area minimizing currents with arbitrary codimension and multiplicity
di: Nardulli, Stefano, et al.
Pubblicazione: (2022)

Lipschitz approximation for general almost area minimizing currents
di: Resende, Reinaldo
Pubblicazione: (2023)

Designing a Linearized Potential Function in Neural Network Optimization Using Csiszár Type of Tsallis Entropy
di: Akiyama, Keito
Pubblicazione: (2024)

Multiplicity results for mass constrained Allen-Cahn equations on Riemannian manifolds with boundary
di: Corona, Dario, et al.
Pubblicazione: (2024)

On Polyconvexity and Almgren Uniform Ellipticity With Respect to Polyhedral Test Pairs
di: Lesniak, Maciej
Pubblicazione: (2025)

Local and global minimality of the lamella for the anisotropic Ohta-Kawasaki energy
di: Fiorini, Alberto
Pubblicazione: (2026)

A refined Lusin type theorem for gradients
di: De Masi, Luigi, et al.
Pubblicazione: (2024)

On existence and uniqueness for transport equations with non-smooth velocity fields under inhomogeneous Dirichlet data
di: Eto, Tokuhiro, et al.
Pubblicazione: (2025)

The ratio-cut polytope and K-means clustering
di: De Rosa, Antonio, et al.
Pubblicazione: (2020)

On the equivalence between static and dynamic optimal transport governed by linear control systems
di: Einav, Amit, et al.
Pubblicazione: (2025)

Training-Induced Escape from Token Clustering in a Mean-Field Formulation of Transformers
di: Isobe, Noboru, et al.
Pubblicazione: (2026)

Structure of two-dimensional mod$(q)$ area-minimizing currents near flat singularities: the codimension one case
di: Skorobogatova, Anna, et al.
Pubblicazione: (2025)

Variational models of robust optimal transport
di: De Masi, Luigi, et al.
Pubblicazione: (2025)

On the regularity of area minimizing currents at boundaries with arbitrary multiplicity
di: Fleschler, Ian, et al.
Pubblicazione: (2024)

Interior regularity of area minimizing currents within a $C^{2,α}$-submanifold
di: Nardulli, Stefano, et al.
Pubblicazione: (2024)

Area minimizing hypersurfaces modulo $p$: a geometric free-boundary problem
di: De Lellis, Camillo, et al.
Pubblicazione: (2021)

Excess decay for minimizing hypercurrents mod $2Q$
di: De Lellis, Camillo, et al.
Pubblicazione: (2023)

Energy-minimizing torus-valued maps with prescribed singularities, Plateau's problem, and BV-lifting
di: Canevari, Giacomo, et al.
Pubblicazione: (2023)

Anti-Context-Free languages
di: Cardó, Carles
Pubblicazione: (2024)

Neural Network Approximation: A View from Polytope Decomposition
di: Li, ZeYu, et al.
Pubblicazione: (2026)

Convergence of drift-diffusion PDEs arising as Wasserstein gradient flows of convex functions
di: Chizat, Lénaïc, et al.
Pubblicazione: (2025)

An efficient volume-preserving MBO scheme for data clustering and classification
di: Krämer, Fabius, et al.
Pubblicazione: (2024)

Sharp upper bound for a branched transport problem coming from Ginzburg-Landau models
di: Cosenza, Alessandro, et al.
Pubblicazione: (2026)

Ahlfors-regularity for minimizers of a multiphase optimal design problem
di: Esposito, Luca, et al.
Pubblicazione: (2025)