Image de couverture de livre

Cascade Token Selection for Transformer Attention Acceleration

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteur principal:	Thomas, Stephen J.
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning Artificial Intelligence 65F10, 68T07, 90C30
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Gated Subspace Inference for Transformer Acceleration
par: Thomas, Stephen J.
Publié: (2026)

SVD-Preconditioned Gradient Descent Method for Solving Nonlinear Least Squares Problems
par: Chang, Zhipeng, et autres
Publié: (2026)

A Layer Separation Optimization Framework for Cross-Entropy Training in Deep Learning
par: Liu, Yaru, et autres
Publié: (2026)

Holonorm
par: Yongueng, Daryl Noupa, et autres
Publié: (2025)

Faster Adaptive Optimization via Expected Gradient Outer Product Reparameterization
par: DePavia, Adela, et autres
Publié: (2025)

A Neural-Operator Preconditioned Newton Method for Accelerated Nonlinear Solvers
par: Lee, Youngkyu, et autres
Publié: (2025)

Objective Value Change and Shape-Based Accelerated Optimization for the Neural Network Approximation
par: Xie, Pengcheng, et autres
Publié: (2025)

Progressive Power Homotopy for Non-convex Optimization
par: Xu, Chen
Publié: (2026)

Global Optimization with A Power-Transformed Objective and Gaussian Smoothing
par: Xu, Chen
Publié: (2024)

Sample-wise Constrained Learning via a Sequential Penalty Approach with Applications in Image Processing
par: Lanzillotta, Francesca, et autres
Publié: (2026)

Effectively Leveraging Momentum Terms in Stochastic Line Search Frameworks for Fast Optimization of Finite-Sum Problems
par: Lapucci, Matteo, et autres
Publié: (2024)

Convergence Conditions for Stochastic Line Search Based Optimization of Over-parametrized Models
par: Lapucci, Matteo, et autres
Publié: (2024)

A Hybrid Iterative Neural Solver Based on Spectral Analysis for Parametric PDEs
par: Cui, Chen, et autres
Publié: (2024)

Power Homotopy for Zeroth-Order Non-Convex Optimizations
par: Xu, Chen
Publié: (2025)

Error Bound Analysis for the Regularized Loss of Deep Linear Neural Networks
par: Chen, Po, et autres
Publié: (2025)

Towards Solving Polynomial-Objective Integer Programming with Hypergraph Neural Networks
par: Li, Minshuo, et autres
Publié: (2026)

Two-level overlapping additive Schwarz preconditioner for training scientific machine learning applications
par: Lee, Youngkyu, et autres
Publié: (2024)

Enhancing training of physics-informed neural networks using domain-decomposition based preconditioning strategies
par: Kopaničáková, Alena, et autres
Publié: (2023)

Refining Graphical Neural Network Predictions Using Flow Matching for Optimal Power Flow with Constraint-Satisfaction Guarantee
par: Khanal, Kshitiz
Publié: (2025)

Generalizing Adam to Manifolds for Efficiently Training Transformers
par: Brantner, Benedikt
Publié: (2023)

Hybrid Least Squares/Gradient Descent Methods for DeepONets
par: Choi, Jun, et autres
Publié: (2025)

Inter-Layer Hessian Analysis of Neural Networks with DAG Architectures
par: Bolshim, Maxim, et autres
Publié: (2026)

Stochastic Estimation of the Layer-wise Hessian Trace for Monitoring Neural-network Training
par: Bolshim, Maxim, et autres
Publié: (2026)

Local properties of neural networks through the lens of layer-wise Hessians
par: Bolshim, Maxim, et autres
Publié: (2025)

An Augmented Lagrangian Method for Training Recurrent Neural Networks
par: Wang, Yue, et autres
Publié: (2024)

BROS: Bias-Corrected Randomized Subspaces for Memory-Efficient Single-Loop Bilevel Optimization
par: Zhang, Hengrui, et autres
Publié: (2026)

On the fast convergence of minibatch heavy ball momentum
par: Bollapragada, Raghu, et autres
Publié: (2022)

Randomized Matrix Sketching for Neural Network Training and Gradient Monitoring
par: Antil, Harbir, et autres
Publié: (2025)

Preconditioned subgradient method for composite optimization: overparameterization and fast convergence
par: Díaz, Mateo, et autres
Publié: (2025)

A Paired Autoencoder Framework for Inverse Problems via Bayes Risk Minimization
par: Hart, Emma, et autres
Publié: (2025)

Residual Multi-Fidelity Neural Network Computing
par: Davis, Owen, et autres
Publié: (2023)

Edge-Wise Graph-Instructed Neural Networks
par: Della Santa, Francesco, et autres
Publié: (2024)

Have ASkotch: A Neat Solution for Large-scale Kernel Ridge Regression
par: Rathore, Pratik, et autres
Publié: (2024)

Iterative Methods for Full-Scale Gaussian Process Approximations for Large Spatial Data
par: Gyger, Tim, et autres
Publié: (2024)

Volume-Preserving Transformers for Learning Time Series Data with Structure
par: Brantner, Benedikt, et autres
Publié: (2023)

Deep Adaptive Dimension Reduction for Bayesian Inference in Inverse Problems
par: Wang, Yueyang, et autres
Publié: (2026)

Auto-exploration for online reinforcement learning
par: Ju, Caleb, et autres
Publié: (2025)

SplInterp: Improving our Understanding and Training of Sparse Autoencoders
par: Budd, Jeremy, et autres
Publié: (2025)

Convergence of gradient descent for deep neural networks
par: Chatterjee, Sourav
Publié: (2022)

Kernel Alignment for Unsupervised Feature Selection via Matrix Factorization
par: Lin, Ziyuan, et autres
Publié: (2024)