Image de couverture de livre

Support Basis: Fast Attention Beyond Bounded Entries

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Aliakbarpour, Maryam, Braverman, Vladimir, Yin, Junze, Zhang, Haochen
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

High-Dimensional Robust Mean Estimation with Untrusted Batches
par: Aliakbarpour, Maryam, et autres
Publié: (2026)

CoVE: Compressed Vocabulary Expansion Makes Better LLM-based Recommender Systems
par: Zhang, Haochen, et autres
Publié: (2025)

Breaking the Frozen Subspace: Importance Sampling for Low-Rank Optimization in LLM Pretraining
par: Zhang, Haochen, et autres
Publié: (2025)

High-Probability Bounds For Heterogeneous Local Differential Privacy
par: Aliakbarpour, Maryam, et autres
Publié: (2025)

Auditing Information Disclosure During LLM-Scale Gradient Descent Using Gradient Uniqueness
par: Abdelghafar, Sleem, et autres
Publié: (2025)

Conv-Basis: A New Paradigm for Efficient Attention Inference and Gradient Computation in Transformers
par: Liang, Yingyu, et autres
Publié: (2024)

Solving Attention Kernel Regression Problem via Pre-conditioner
par: Song, Zhao, et autres
Publié: (2023)

Optimal Prediction-Augmented Algorithms for Testing Independence of Distributions
par: Aliakbarpour, Maryam, et autres
Publié: (2026)

Fast and Efficient Matching Algorithm with Deadline Instances
par: Song, Zhao, et autres
Publié: (2023)

Optimal Algorithms for Augmented Testing of Discrete Distributions
par: Aliakbarpour, Maryam, et autres
Publié: (2024)

Better Private Distribution Testing by Leveraging Unverified Auxiliary Data
par: Aliakbarpour, Maryam, et autres
Publié: (2025)

How fast can you find a good hypothesis?
par: Aamand, Anders, et autres
Publié: (2025)

Privacy in Metalearning and Multitask Learning: Modeling and Separations
par: Aliakbarpour, Maryam, et autres
Publié: (2024)

Fixed Design Analysis of Regularization-Based Continual Learning
par: Li, Haoran, et autres
Publié: (2023)

Adversarially robust quantum state learning and testing
par: Aliakbarpour, Maryam, et autres
Publié: (2025)

Nearly-Linear Time Private Hypothesis Selection with the Optimal Approximation Factor
par: Aliakbarpour, Maryam, et autres
Publié: (2025)

Gap-Dependent Bounds for Federated $Q$-learning
par: Zhang, Haochen, et autres
Publié: (2025)

Accelerating Attention with Basis Decomposition
par: Zhao, Jialin
Publié: (2025)

Binary Hypothesis Testing for Softmax Models and Leverage Score Models
par: Gu, Yuzhou, et autres
Publié: (2024)

An Iterative Algorithm for Rescaled Hyperbolic Functions Regression
par: Gao, Yeqi, et autres
Publié: (2023)

On the Structure of Replicable Hypothesis Testers
par: Aamand, Anders, et autres
Publié: (2025)

Enhancing Feature-Specific Data Protection via Bayesian Coordinate Differential Privacy
par: Aliakbarpour, Maryam, et autres
Publié: (2024)

Memory-Statistics Tradeoff in Continual Learning with Structural Regularization
par: Li, Haoran, et autres
Publié: (2025)

Gap-Dependent Bounds for Q-Learning using Reference-Advantage Decomposition
par: Zheng, Zhong, et autres
Publié: (2024)

Metalearning with Very Few Samples Per Task
par: Aliakbarpour, Maryam, et autres
Publié: (2023)

BasisFormer: Attention-based Time Series Forecasting with Learnable and Interpretable Basis
par: Ni, Zelin, et autres
Publié: (2023)

Gap-Dependent Bounds for Nearly Minimax Optimal Reinforcement Learning with Linear Function Approximation
par: Zhang, Haochen, et autres
Publié: (2026)

Gradient Shaping Beyond Clipping: A Functional Perspective on Update Magnitude Control
par: You, Haochen, et autres
Publié: (2025)

Efficient Alternating Minimization with Applications to Weighted Low Rank Approximation
par: Song, Zhao, et autres
Publié: (2023)

Inverting the Leverage Score Gradient: An Efficient Approximate Newton Method
par: Li, Chenyang, et autres
Publié: (2024)

Chunk-wise Attention Transducers for Fast and Accurate Streaming Speech-to-Text
par: Xu, Hainan, et autres
Publié: (2026)

FastDSAC: Unlocking the Potential of Maximum Entropy RL in High-Dimensional Humanoid Control
par: Xue, Jun, et autres
Publié: (2026)

Entry-Specific Bounds for Low-Rank Matrix Completion under Highly Non-Uniform Sampling
par: Xi, Xumei, et autres
Publié: (2024)

Learning-augmented Maximum Independent Set
par: Braverman, Vladimir, et autres
Publié: (2024)

Dynamic Maintenance of Kernel Density Estimation Data Structure: From Practice to Theory
par: Liang, Jiehao, et autres
Publié: (2022)

How to Inverting the Leverage Score Distribution?
par: Li, Zhihang, et autres
Publié: (2024)

Low Rank Matrix Completion via Robust Alternating Minimization in Nearly Linear Time
par: Gu, Yuzhou, et autres
Publié: (2023)

FastAttention: Extend FlashAttention2 to NPUs and Low-resource GPUs
par: Lin, Haoran, et autres
Publié: (2024)

Learning-Augmented Hierarchical Clustering
par: Braverman, Vladimir, et autres
Publié: (2025)

Computational Algebra with Attention: Transformer Oracles for Border Basis Algorithms
par: Kera, Hiroshi, et autres
Publié: (2025)