Cover Image

Pay Attention to Attention Distribution: A New Local Lipschitz Bound for Transformers

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Yudin, Nikolay, Gaponov, Alexander, Kudriashov, Sergei, Rakhuba, Maxim
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Numerical Analysis 15A42, 15A60, 68T07
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

DyKAF: Dynamical Kronecker Approximation of the Fisher Information Matrix for Gradient Preconditioning
by: Yudin, Nikolay, et al.
Published: (2025)

Lambda admissible subspaces of self adjoint matrices
by: Zuccalli, Francisco Arrieta, et al.
Published: (2026)

Efficient Bounds and Estimates for Canonical Angles in Randomized Subspace Approximations
by: Dong, Yijun, et al.
Published: (2022)

Nonlocal techniques for the analysis of deep ReLU neural network approximations
by: Schneider, Cornelia, et al.
Published: (2025)

Sharp error bounds for approximate eigenvalues and singular values from subspace methods
by: Haas, Irina-Beatrice, et al.
Published: (2025)

Matrix perturbation analysis of methods for extracting singular values from approximate singular subspaces
by: Lazzarino, Lorenzo, et al.
Published: (2024)

A randomized preconditioned Cholesky-QR algorithm
by: Garrison, James E., et al.
Published: (2024)

Optimization on the Extended Tensor-Train Manifold with Shared Factors
by: Molozhavenko, Alexander, et al.
Published: (2025)

New duality in choices of feature spaces via kernel analysis
by: Jorgensen, Palle E. T., et al.
Published: (2025)

Neural-Guided Domain Restriction to Accelerate Pseudospectra Computation for Structured Non-normal Banded Matrices
by: Punia, Amit, et al.
Published: (2026)

FieldTNN-based machine learning method for Maxwell eigenvalue problems
by: Jiang, Jiantao, et al.
Published: (2024)

Robust Faber--Schauder approximation based on discrete observations of an antiderivative
by: Han, Xiyue, et al.
Published: (2022)

Solving a Machine Learning Regression Problem Based on the Theory of Random Functions
by: Bakhvalov, Yuriy N.
Published: (2025)

Weak majorization inequalities for the cubic and quartic coefficients of $e^{(A+B)t}$ versus $e^{At}e^{Bt}$
by: Zhang, Teng
Published: (2026)

Matrix Inequalities between $f(A)σf(B)$ and $AσB$
by: Devi, Manisha, et al.
Published: (2023)

On Generalizing Trace Minimization Principles, II
by: Liang, Xin, et al.
Published: (2023)

Neural Networks for Bayesian Inverse Problems Governed by a Nonlinear ODE
by: Villalobos, German, et al.
Published: (2025)

A Variational Equation and Lower Bound for the Linear Least-Squares Backward Error
by: Hallman, Eric
Published: (2026)

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

Galerkin Scheme Using Biorthogonal Wavelets on Intervals for Elliptic Interface Problems
by: Han, Bin, et al.
Published: (2024)

Wavelet-based Galerkin Scheme with Arbitrarily High-Order Convergence for 1D Elliptic Interface Problems
by: Han, Bin, et al.
Published: (2026)

A Note on Eigenvalues of Perturbed Hermitian Matrices
by: Li, Chi-Kwong, et al.
Published: (2025)

Equidistribution-based training of Free Knot Splines and ReLU Neural Networks
by: Appella, Simone, et al.
Published: (2024)

When $D$-companion matrix meets incomplete polynomials
by: Zhang, Teng
Published: (2023)

Solving Coupled Tensor Equation $\mathcal{A} \ltimes \mathcal{X} =\mathcal{B}, \ \mathcal{X}\ltimes \mathcal{C}=\mathcal{D}$ using Semi-Tensor Products in the t-product
by: Wankhede, Mansi, et al.
Published: (2026)

Neural enrichment finite element method: A hybrid framework for problems with strong oscillations or interface problems
by: Guo, Shihan, et al.
Published: (2026)

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

Adaptive Bivariate Quarklet Tree Approximation via Anisotropic Tensor Quarklets
by: Hovemann, Marc
Published: (2025)

Asymptotic estimations of a perturbed symmetric eigenproblem
by: Gissler, Armand, et al.
Published: (2024)

Spectral Transformation for the Dense Symmetric Semidefinite Generalized Eigenvalue Problem
by: Stewart, Michael
Published: (2024)

Approximation of a Multivariate Function of Bounded Variation from its Scattered Data
by: Dachiraju, Rajesh
Published: (2020)

Operator symmetric moduli and sharp triangle inequalities
by: Zhang, Teng
Published: (2026)

Heron-Wasserstein majorization inequalities for spectral and Kubo-Ando geometric means
by: Vuong, Trung Dung, et al.
Published: (2026)

Changing the ranking in eigenvector centrality of a weighted graph by small perturbations
by: Benzi, Michele, et al.
Published: (2025)

Stochastic Rounding Implicitly Regularizes Tall-and-Thin Matrices
by: Dexter, Gregory, et al.
Published: (2024)

Discrete vs. Continuous Trade-offs for Generative Models
by: Korrapati, Jathin, et al.
Published: (2024)

Numerical range for weighted Moore-Penrose inverse of tensor
by: Be, Aaisha, et al.
Published: (2022)

The Error of Deep Operator Networks Is the Sum of Its Parts: Branch-Trunk and Mode Error Decompositions
by: Heinlein, Alexander, et al.
Published: (2026)

Characterization and computation of canonical tight windows for Gabor frames
by: Janssen, A. J. E. M, et al.
Published: (2000)

Multi-Head Attention as Ensemble Nadaraya-Watson Estimation: Variance Reduction, Decorrelation, and Optimal Head Diversity
by: Fokoué, Ernest
Published: (2026)