Copertina

Attention Mechanisms Through the Lens of Numerical Methods: Approximation Methods and Alternative Formulations

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Serret, Michel Fabrice, Cortinovis, Alice, Dong, Yijun, Halikias, Diana, Ma, Anna, Matti, Fabio, Needell, Deanna, Pearce, Katherine J., Rebrova, Elizaveta, Shur, Disha, Smith, Rudi, Wang, Hai-Xiao, Grigori, Laura
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Numerical Analysis
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Randomized Kaczmarz Methods with Beyond-Krylov Convergence
di: Dereziński, Michał, et al.
Pubblicazione: (2025)

Stochastic gradient descent for streaming linear and rectified linear systems with adversarial corruptions
di: Jeong, Halyun, et al.
Pubblicazione: (2024)

Fine-grained Analysis and Faster Algorithms for Iteratively Solving Linear Systems
di: Dereziński, Michał, et al.
Pubblicazione: (2024)

Linear Discriminant Analysis with the Randomized Kaczmarz Method
di: Chi, Jocelyn T., et al.
Pubblicazione: (2022)

Numerical Instabilities in the Kaczmarz Method and Stabilization by Iterative Refinement
di: Dereziński, Michał, et al.
Pubblicazione: (2026)

Understanding Transformers and Attention Mechanisms: An Introduction for Applied Mathematicians
di: Serret, Michel Fabrice
Pubblicazione: (2026)

Block Matrix and Tensor Randomized Kaczmarz Methods for Linear Feasibility Problems
di: Zhang, Minxin, et al.
Pubblicazione: (2024)

On Trimming Tensor-structured Measurements and Efficient Low-rank Tensor Recovery
di: Suryanarayanan, Shambhavi, et al.
Pubblicazione: (2025)

Subspace-constrained randomized coordinate descent for linear systems with good low-rank matrix approximations
di: Lok, Jackie, et al.
Pubblicazione: (2025)

Learning nonnegative matrix factorizations from compressed data
di: Chaudhry, Abraar, et al.
Pubblicazione: (2024)

A subspace constrained randomized Kaczmarz method for structure or external knowledge exploitation
di: Lok, Jackie, et al.
Pubblicazione: (2023)

Stochastic Iterative Methods for Online Rank Aggregation from Pairwise Comparisons
di: Jarman, Benjamin, et al.
Pubblicazione: (2024)

Beyond Expectation: Concentration Inequalities for Randomized Iterative Methods
di: Anderson, Toby, et al.
Pubblicazione: (2025)

Riemannian Archetypal Analysis: Interpretable non-linear data analysis on deformed star distributions
di: Diepeveen, Willem, et al.
Pubblicazione: (2026)

Manifold Learning with Normalizing Flows: Towards Regularity, Expressivity and Iso-Riemannian Geometry
di: Diepeveen, Willem, et al.
Pubblicazione: (2025)

Kernel Alignment for Unsupervised Feature Selection via Matrix Factorization
di: Lin, Ziyuan, et al.
Pubblicazione: (2024)

Alice94/MatrixFunctions-Banded-HSS: MatrixFunction-Banded-HSS v1.0.0
di: Alice Cortinovis
Pubblicazione: (2025)

Towards Universal Convergence of Backward Error in Linear System Solvers
di: Dereziński, Michał, et al.
Pubblicazione: (2026)

Error dynamics of mini-batch gradient descent with random reshuffling for least squares regression
di: Lok, Jackie, et al.
Pubblicazione: (2024)

On Regularization via Early Stopping for Least Squares Regression
di: Sonthalia, Rishi, et al.
Pubblicazione: (2024)

Quantile Randomized Kaczmarz Algorithm with Whitelist Trust Mechanism
di: Shvaiko, Sofiia, et al.
Pubblicazione: (2026)

Stable Phase Retrieval: Optimal Rates in Poisson and Heavy-tailed Models
di: Huang, Gao, et al.
Pubblicazione: (2025)

Stochastic Gradient Descent for Incomplete Tensor Linear Systems
di: Ma, Anna, et al.
Pubblicazione: (2025)

Observational Multiplicity
di: George, Erin, et al.
Pubblicazione: (2025)

Randomized Kaczmarz in Adversarial Distributed Setting
di: Huang, Longxiu, et al.
Pubblicazione: (2023)

Cauchy Random Features for Operator Learning in Sobolev Space
di: Liao, Chunyang, et al.
Pubblicazione: (2025)

Curvature Corrected Nonnegative Manifold Data Factorization
di: Chew, Joyce, et al.
Pubblicazione: (2025)

Random Vector Functional Link Networks for Function Approximation on Manifolds
di: Needell, Deanna, et al.
Pubblicazione: (2020)

What is (de)politicization and what is wrong with it?
di: Dimitrios Halikias
Pubblicazione: (2026)

A sublinear-time randomized algorithm for column and row subset selection based on strong rank-revealing QR factorizations
di: Cortinovis, Alice, et al.
Pubblicazione: (2024)

Detecting when one probe vector is enough for preconditioned log-determinant approximation
di: Cortinovis, Alice, et al.
Pubblicazione: (2026)

Adaptive randomized pivoting for column subset selection, DEIM, and low-rank approximation
di: Cortinovis, Alice, et al.
Pubblicazione: (2024)

A federated Kaczmarz algorithm
di: Jeong, Halyun, et al.
Pubblicazione: (2025)

Improved bounds for randomized Schatten norm estimation of numerically low-rank matrices
di: Chu, Ya-Chi, et al.
Pubblicazione: (2024)

Learn to Evolve: Self-supervised Neural JKO Operator for Wasserstein Gradient Flow
di: Feng, Xue, et al.
Pubblicazione: (2026)

Convergence and Complexity Guarantee for Inexact First-order Riemannian Optimization Algorithms
di: Li, Yuchen, et al.
Pubblicazione: (2024)

Harnessing the Power of Sample Abundance: Theoretical Guarantees and Algorithms for Accelerated One-Bit Sensing
di: Eamaz, Arian, et al.
Pubblicazione: (2023)

Harmful Overfitting in Sobolev Spaces
di: Karhadkar, Kedar, et al.
Pubblicazione: (2026)

Differentially Private Random Feature Model
di: Liao, Chunyang, et al.
Pubblicazione: (2024)

Convergence and complexity of block majorization-minimization for constrained block-Riemannian optimization
di: Li, Yuchen, et al.
Pubblicazione: (2023)