English
Related papers

Related papers: How Does Attention Help? Insights from Random Matr…

200 papers

The attention operator is arguably the key distinguishing factor of transformer architectures, which have demonstrated state-of-the-art performance on a variety of tasks. However, transformer attention operators often impose a significant…

Machine Learning · Computer Science 2024-12-24 Ziyang Wu , Tianjiao Ding , Yifu Lu , Druv Pai , Jingyuan Zhang , Weida Wang , Yaodong Yu , Yi Ma , Benjamin D. Haeffele

Attention mechanisms are often used in deep neural networks for distantly supervised relation extraction (DS-RE) to distinguish valid from noisy instances. However, traditional 1-D vector attention models are insufficient for the learning…

Computation and Language · Computer Science 2018-09-05 Jinhua Du , Jingguang Han , Andy Way , Dadong Wan

First derived from human intuition, later adapted to machine translation for automatic token alignment, attention mechanism, a simple method that can be used for encoding sequence data based on the importance score each element is assigned,…

Computation and Language · Computer Science 2018-11-15 Dichao Hu

Random-matrix theory helps disentangle signal from noise in large data sets. We analyze rectangular $p \times q$ matrices $W = W_0 + M$ in which the noise $M$ generates a Marchenko-Pastur bulk, whereas the signal $W_0$ injects an extensive…

Disordered Systems and Neural Networks · Physics 2025-11-25 Niklas Forner , Alexander Maloney , Bernd Rosenow

Linear-attention models that compress the entire input sequence into a fixed-size recurrent state offer an efficient alternative to Transformers, but their finite memory induces forgetfulness that harms retrieval-intensive tasks. To…

Computation and Language · Computer Science 2025-10-27 Mutian He , Philip N. Garner

Transformer-based deep learning models have achieved state-of-the-art performance across numerous language and vision tasks. While the self-attention mechanism, a core component of transformers, has proven capable of handling complex data…

Machine Learning · Computer Science 2025-08-05 Laziz Abdullaev , Tan M. Nguyen

Despite the advantageous subquadratic complexity of modern recurrent deep learning models -- such as state-space models (SSMs) -- recent studies have highlighted their potential shortcomings compared to transformers on reasoning and…

Machine Learning · Computer Science 2025-10-13 Destiny Okpekpe , Antonio Orvieto

Self-attention, as the key block of transformers, is a powerful mechanism for extracting features from the inputs. In essence, what self-attention does is to infer the pairwise relations between the elements of the inputs, and modify the…

Machine Learning · Computer Science 2021-03-09 Lemeng Wu , Xingchao Liu , Qiang Liu

A sample covariance matrix $\boldsymbol{S}$ of completely observed data is the key statistic in a large variety of multivariate statistical procedures, such as structured covariance/precision matrix estimation, principal component analysis,…

Methodology · Statistics 2021-04-20 Seongoh Park , Xinlei Wang , Johan Lim

The self-attention mechanism, while foundational to modern Transformer architectures, suffers from a critical inefficiency: it frequently allocates substantial attention to redundant or noisy context. Differential Attention addressed this…

This paper reveals that we can interpret the fundamental function of Randomized Time Warping (RTW) as a type of self-attention mechanism, a core technology of Transformers in motion recognition. The self-attention is a mechanism that…

Computer Vision and Pattern Recognition · Computer Science 2025-08-25 Yutaro Hiraoka , Kazuya Okamura , Kota Suto , Kazuhiro Fukui

In recent years, the long-range attention mechanism of vision transformers has driven significant performance breakthroughs across various computer vision tasks. However, the traditional self-attention mechanism, which processes both…

Computer Vision and Pattern Recognition · Computer Science 2024-11-05 Tianyi Zhang , Baoxin Li , Jae-sun Seo , Yu Cao

Multi-head, key-value attention is the backbone of the widely successful Transformer model and its variants. This attention mechanism uses multiple parallel key-value attention blocks (called heads), each performing two fundamental…

Machine Learning · Computer Science 2022-02-15 Sarthak Mittal , Sharath Chandra Raparthy , Irina Rish , Yoshua Bengio , Guillaume Lajoie

Latest development of neural models has connected the encoder and decoder through a self-attention mechanism. In particular, Transformer, which is solely based on self-attention, has led to breakthroughs in Natural Language Processing (NLP)…

Computation and Language · Computer Science 2019-11-07 Xindian Ma , Peng Zhang , Shuai Zhang , Nan Duan , Yuexian Hou , Dawei Song , Ming Zhou

Transformers and deep state space models (SSMs) sit at opposite ends of a basic design choice: attention routes each query through a growing key-value (KV) cache by content-based matching at quadratic cost, while deep SSMs compress context…

Machine Learning · Computer Science 2026-05-26 Naoki Kiyohara , Harrison Bo Hua Zhu , Riccardo El Hassanin , Zhuo Sun , Wenlong Chen , Samir Bhatt , Yingzhen Li

The Transformer model is widely successful on many natural language processing tasks. However, the quadratic complexity of self-attention limit its application on long text. In this paper, adopting a fine-to-coarse attention mechanism on…

Computation and Language · Computer Science 2019-11-12 Zihao Ye , Qipeng Guo , Quan Gan , Xipeng Qiu , Zheng Zhang

We study the low-rank phase retrieval problem, where we try to recover a $d_1\times d_2$ low-rank matrix from a series of phaseless linear measurements. This is a fourth-order inverse problem, as we are trying to recover factors of matrix…

Information Theory · Computer Science 2020-07-07 Kiryung Lee , Sohail Bahmani , Yonina Eldar , Justin Romberg

Two-phase sampling designs are frequently employed in epidemiological studies and large-scale health surveys. In such designs, certain variables are exclusively collected within a second-phase random subsample of the initial first-phase…

Methodology · Statistics 2024-03-25 Lingxiao Wang

We present a formal operator-theoretic framework for analyzing Transformer-based language models using free probability theory. By modeling token embeddings and attention mechanisms as self-adjoint operators in a tracial \( W^*…

Machine Learning · Computer Science 2025-08-19 Swagatam Das

Sequence models face a fundamental tradeoff between memory capacity and computational efficiency. Transformers achieve expressive context modeling at quadratic cost, while linear attention and state-space models run in linear time by…

Machine Learning · Computer Science 2026-05-11 Yaxita Amin , Helen Zichen Li , Mengfan Zhang , Samet Ayhan