English
Related papers

Related papers: Token Sample Complexity of Attention

200 papers

The quadratic cost of softmax attention limits Transformer scalability in high-resolution vision. We introduce Infinite Self-Attention (InfSA), a spectral reformulation that treats each attention layer as a diffusion step on a…

Computer Vision and Pattern Recognition · Computer Science 2026-03-31 Giorgio Roffo , Hazem Abdelkawy , Nilli Lavie , Luke Palmer

Large language models (LLMs) have demonstrated strong performance on a variety of natural language processing (NLP) tasks. However, they often struggle with long-text sequences due to the ``lost in the middle'' phenomenon. This issue has…

Computation and Language · Computer Science 2025-12-16 Zewen Qiang , Sendong Zhao , Haochun Wang , Bing Qin , Ting Liu

The transformer is the most popular neural architecture for language modeling. The cornerstone of the transformer is its global attention mechanism, which lets the model aggregate information from all preceding tokens before generating the…

Computation and Language · Computer Science 2026-05-20 Jiaoda Li , Ryan Cotterell

Large language models spend most of their inference cost on attention over long contexts, yet empirical behavior suggests that only a small subset of tokens meaningfully contributes to each query. We formalize this phenomenon by modeling…

Artificial Intelligence · Computer Science 2026-02-17 Vashista Nobaub

As the demand for processing extended textual data grows, the ability to handle long-range dependencies and maintain computational efficiency is more critical than ever. One of the key issues for long-sequence modeling using attention-based…

Computation and Language · Computer Science 2025-05-26 Aosong Feng , Rex Ying , Leandros Tassiulas

While Transformers have shown remarkable success in natural language processing, their attention mechanism's large memory requirements have limited their ability to handle longer contexts. Prior approaches, such as recurrent memory or…

Computation and Language · Computer Science 2023-11-21 Amirkeivan Mohtashami , Martin Jaggi

Concentration results say that a sequence of random variables becomes progressively concentrated around the mean. Such results are common in the study of functions of random graphs. We introduce a real-valued logic with various aggregate…

Probability · Mathematics 2026-02-23 Michael Benedikt , Maksim Zhukovskii

The leading term in the normal approximation to the distribution of Student's t statistic is derived in a general setting, with the sole assumption being that the sampled distribution is in the domain of attraction of a normal law. The form…

Probability · Mathematics 2007-05-23 Peter Hall , Qiying Wang

We study how the Shannon entropy of sequences produced by an information source converges to the source's entropy rate. We synthesize several phenomenological approaches to applying information theoretic measures of randomness and memory to…

Statistical Mechanics · Physics 2007-05-23 James P. Crutchfield , David P. Feldman

Transformer has become the dominant architecture for sequence modeling, yet a detailed understanding of how its structural parameters influence expressive power remains limited. In this work, we study the approximation properties of…

Machine Learning · Computer Science 2026-04-01 Penghao Yu , Haotian Jiang , Zeyu Bao , Ruoxi Yu , Qianxiao Li

This paper investigates token homogenization - the convergence of token representations toward uniformity across transformer layers and its relationship to positional bias in large language models. We empirically examine whether…

We establish finite sample bounds for the error of standard and waste-free SMC samplers. Our results cover estimates of both expectations and normalising constants of the target distributions. We consider first an arbitrary sequence of…

Computation · Statistics 2026-04-15 Yvann Le Fay , Nicolas Chopin , Matti Vihola

Understanding whether attention mechanisms converge to the kernel regime is foundational to the validity of influence functions for transformer accountability. Exact NTK characterization of softmax attention is precluded by its exponential…

Machine Learning · Computer Science 2026-05-08 Jose Marie Antonio Miñoza , Paulo Mario P. Medina , Sebastian C. Ibañez

Understanding the reasons behind the exceptional success of transformers requires a better analysis of why attention layers are suitable for NLP tasks. In particular, such tasks require predictive models to capture contextual meaning which…

Machine Learning · Statistics 2024-05-20 Simone Bombari , Marco Mondelli

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

Softmax attention struggles with long contexts due to structural limitations: the strict sum-to-one constraint forces attention sinks on irrelevant tokens, and probability mass disperses as sequence lengths increase. We tackle these…

Machine Learning · Computer Science 2026-04-17 Xingyue Huang , Xueying Ding , Mingxuan Ju , Yozen Liu , Neil Shah , Tong Zhao

We model the transmission of a message on the complete graph with n vertices and limited resources. The vertices of the graph represent servers that may broadcast the message at random. Each server has a random emission capital that…

Probability · Mathematics 2019-02-20 Francis Comets , François Delarue , René Schott

Softmax attention is a central component of transformer architectures, yet its nonlinear structure poses significant challenges for theoretical analysis. We develop a unified, measure-based framework for studying single-layer softmax…

Machine Learning · Computer Science 2025-12-15 Etienne Boursier , Claire Boyer

This article studies the \emph{robust covariance matrix estimation} of a data collection $X = (x_1,\ldots,x_n)$ with $x_i = \sqrt \tau_i z_i + m$, where $z_i \in \mathbb R^p$ is a \textit{concentrated vector} (e.g., an elliptical random…

Probability · Mathematics 2022-04-12 Cosme Louart , Romain Couillet

Recently, the scaling limit of cluster sizes for critical inhomogeneous random graphs of rank-1 type having finite variance but infinite third moment degrees was obtained (see previous work by Bhamidi, van der Hofstad and van Leeuwaarden).…

Probability · Mathematics 2014-04-09 Remco van der Hofstad , Sandra Kliem , Johan S. H. van Leeuwaarden