Cover Image

A Unified Framework for Critical Scaling of Inverse Temperature in Self-Attention

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Hayase, Tomohiro, Karakida, Ryo
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Probability 68T07, 41A60, 82B26, 60G70 G.3; I.2.7
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

VORT: Adaptive Power-Law Memory for NLP Transformers
by: Mlaiki, Nabil
Published: (2026)

Extremal regime for one-dimensional Mott variable-range hopping
by: Croydon, David A., et al.
Published: (2022)

Gaussian free field on the tree subject to a hard wall II: Asymptotics
by: Fels, Maximilian, et al.
Published: (2024)

Gaussian free field on the tree subject to a hard wall I: Bounds
by: Fels, Maximilian, et al.
Published: (2024)

Cover times of many random walkers on a discrete network
by: Kim, Hyunjoong, et al.
Published: (2023)

Aging and sub-aging for one-dimensional random walks amongst random conductances
by: Croydon, David A., et al.
Published: (2023)

Latent-Autoregressive GP-VAE Language Model
by: Ruffenach, Yves
Published: (2025)

An asymptotic expansion of the norm of $e^{-|{t-s}|}{1}_{\{0\le s,t\le T\}}$ in the canonical Hilbert space of fractional Brownian motion
by: Chen, Yong
Published: (2025)

Cover times with stochastic resetting
by: Linn, Samantha, et al.
Published: (2024)

Mixed memories in Hopfield networks
by: Gayrard, Véronique
Published: (2025)

Anomalous scaling regime for one-dimensional Mott variable-range hopping
by: Croydon, David A., et al.
Published: (2020)

Non-directed polymers in random environments with range penalties: the high dimensional case
by: Torri, Niccolo, et al.
Published: (2025)

Near-optimal estimates for the $\ell^p$-Lipschitz constants of deep random ReLU neural networks
by: Dirksen, Sjoerd, et al.
Published: (2025)

Upper and lower bounds for the Lipschitz constant of random neural networks
by: Geuchen, Paul, et al.
Published: (2023)

Second Order Asymptotics for the Hard Wall Probability of the 2D Harmonic Crystal
by: Fels, Maximilian, et al.
Published: (2026)

Graph distance and effective resistance of the four-dimensional random walk trace
by: Shiraishi, Daisuke, et al.
Published: (2026)

Sinaĭ excursions: An analogue of Sparre Andersen's formula for the area process of a random walk
by: Donderwinkel, Serte, et al.
Published: (2024)

Height-offset variables and pinning at infinity for gradient Gibbs measures on trees
by: Henning, Florian, et al.
Published: (2024)

A Ray-Knight theorem for $\nablaϕ$ interface models and scaling limits
by: Deuschel, Jean-Dominique, et al.
Published: (2022)

On multidimensional elephant random walk with stops and random step sizes
by: Ghosh, Shyan, et al.
Published: (2026)

Criticality conditions in the Derrida-Retaux model with a random number of terms
by: Lotnikov, Alexey, et al.
Published: (2025)

Scaling limit for the random walk on critical lattice trees
by: Arous, Gérard Ben, et al.
Published: (2025)

A parametric approach to the estimation of convex risk functionals based on Wasserstein distance
by: Nendel, Max, et al.
Published: (2022)

Convergence of three-dimensional loop-erased random walk in the natural parametrization
by: Li, Xinyi, et al.
Published: (2018)

From 1 to infinity: The log-correction for the maximum of variable-speed branching Brownian motion
by: Alban, Alexander, et al.
Published: (2024)

Large deviation principles and functional limit theorems in the deep limit of wide random neural networks
by: Di Lillo, Simmaco, et al.
Published: (2026)

A Probabilistic Proof for Stable Fluctuations in the Extremal Process of Branching Brownian Motion
by: Hartung, Lisa, et al.
Published: (2025)

Density of imaginary multiplicative chaos via Malliavin calculus
by: Aru, Juhan, et al.
Published: (2020)

Birth of a gap: Critical phenomena in 2D Coulomb gas
by: Allard, Matthias, et al.
Published: (2025)

Scaling limits for nonlinear functionals of the discrete Gaussian free field with degenerate random conductances
by: Peter, Christof F., et al.
Published: (2026)

Partition function of 2D Coulomb gases with radially symmetric potentials and a hard wall
by: Allard, Matthias, et al.
Published: (2025)

Asymptotics for the percolation threshold of finitary random interlacements in four and higher dimensions
by: Bi, Yijie, et al.
Published: (2025)

Explicit correlation functions for the six-vertex model in the free-fermion regime
by: Johnston, Samuel G. G., et al.
Published: (2025)

Elephant random walks on infinite Cayley trees
by: Mukherjee, Soumendu Sundar
Published: (2025)

Phase Transitions in the Fluctuations of Functionals of Random Neural Networks
by: Di Lillo, Simmaco, et al.
Published: (2026)

A diffusion model of surface soil pollution based on planar finite-velocity stochastic motion with random lifetime
by: Kolesnik, Alexander D.
Published: (2025)

Caputo fractional stochastic differential equations: Lipschitz continuity in the fractional order
by: Son, T. C., et al.
Published: (2024)

Sharp asymptotics of disconnection time of large cylinders by simple and biased random walks
by: Li, Xinyi, et al.
Published: (2024)

Scaling limit and tail bounds for a random walk model of SOS level lines
by: Hegde, Milind, et al.
Published: (2025)

From quenched invariance principle to semigroup convergence with applications to exclusion processes
by: Chiarini, Alberto, et al.
Published: (2023)