English
Related papers

Related papers: Token Sample Complexity of Attention

200 papers

Attention mechanism is a central component of the transformer architecture which led to the phenomenal success of large language models. However, the theoretical principles underlying the attention mechanism are poorly understood,…

Machine Learning · Computer Science 2023-12-11 Davoud Ataee Tarzanagh , Yingcong Li , Xuechen Zhang , Samet Oymak

We take a deep look into the behavior of self-attention heads in the transformer architecture. In light of recent work discouraging the use of attention distributions for explaining a model's behavior, we show that attention distributions…

Machine Learning · Computer Science 2021-01-15 Damian Pascual , Gino Brunner , Roger Wattenhofer

The rate of convergence of the distribution of the length of the longest increasing subsequence, toward the maximal eigenvalue of certain matrix ensembles, is investigated. For finite-alphabet uniform and nonuniform i.i.d. sources, a rate…

Probability · Mathematics 2012-11-30 Christian Houdré , Zsolt Talata

We consider first-passage percolation on the $d$ dimensional cubic lattice for $d \geq 2$; that is, we assign independently to each edge $e$ a nonnegative random weight $t_e$ with a common distribution and consider the induced random graph…

Probability · Mathematics 2016-04-21 Michael Damron , Naoki Kubota

Token representation strategies within large-scale neural architectures often rely on contextually refined embeddings, yet conventional approaches seldom encode structured relationships explicitly within token interactions. Self-attention…

Computation and Language · Computer Science 2025-03-27 James Blades , Frederick Somerfield , William Langley , Susan Everingham , Maurice Witherington

Sparse Attention is a technique that approximates standard attention computation with sub-quadratic complexity. This is achieved by selectively ignoring smaller entries in the attention matrix during the softmax function computation.…

Machine Learning · Computer Science 2025-02-13 Yichuan Deng , Zhao Song , Jing Xiong , Chiwun Yang

Document-level Neural Machine Translation (DocNMT) has been proven crucial for handling discourse phenomena by introducing document-level context information. One of the most important directions is to input the whole document directly to…

Computation and Language · Computer Science 2023-09-26 Zihan Liu , Zewei Sun , Shanbo Cheng , Shujian Huang , Mingxuan Wang

Sequence-to-sequence (encoder-decoder) models with attention constitute a cornerstone of deep learning research, as they have enabled unprecedented sequential data modeling capabilities. This effectiveness largely stems from the capacity of…

Artificial Intelligence · Computer Science 2018-10-31 Aristotelis Charalampous , Sotirios Chatzis

Recent diffusion models enable high-quality video generation, but suffer from slow runtimes. The large transformer-based backbones used in these models are bottlenecked by spatiotemporal attention. In this paper, we identify that a…

Computer Vision and Pattern Recognition · Computer Science 2026-03-06 Shai Yehezkel , Shahar Yadin , Noam Elata , Yaron Ostrovsky-Berman , Bahjat Kawar

This note describes non-asymptotic variance and tail bounds for order statistics of samples of independent identically distributed random variables. Those bounds are checked to be asymptotically tight when the sampling distribution belongs…

Probability · Mathematics 2012-11-05 Stephane Boucheron , Maud Thomas

We obtain non asymptotic concentration bounds for two kinds of stochastic approximations. We first consider the deviations between the expectation of a given function of the Euler scheme of some diffusion process at a fixed deterministic…

Probability · Mathematics 2012-12-12 Noufel Frikha , Stephane Menozzi

Policy evaluation in reinforcement learning is often conducted using two-timescale stochastic approximation, which results in various gradient temporal difference methods such as GTD(0), GTD2, and TDC. Here, we provide convergence rate…

Machine Learning · Computer Science 2019-12-05 Gal Dalal , Balazs Szorenyi , Gugan Thoppe

The lossless data compression algorithm based on Bayesian Attention Networks is derived from first principles. Bayesian Attention Networks are defined by introducing an attention factor per a training sample loss as a function of two sample…

Machine Learning · Computer Science 2021-03-30 Michael Tetelman

State-of-the-art attention based models, mostly centered around the transformer architecture, solve the problem of sequence-to-sequence translation using the so-called scaled dot-product attention. While this technique is highly effective…

Computation and Language · Computer Science 2020-06-09 Anurag Pallaprolu , Radha Vaidya , Aditya Swaroop Attawar

Evaluating softmax attention over a fixed long context requires reading every cached key-value pair for each new query token. For a given context (a book, a manual, a legal corpus) the attention output is a deterministic function of the…

Machine Learning · Computer Science 2026-05-12 João Monteiro , Michal Klein , Pierre Ablin , Marco Cuturi

Soft attention is a critical mechanism powering LLMs to locate relevant parts within a given context. However, individual attention weights are determined by the similarity of only a single query and key token vector. This "single token…

Computation and Language · Computer Science 2025-07-14 Olga Golovneva , Tianlu Wang , Jason Weston , Sainbayar Sukhbaatar

Transformer has achieved great success in NLP. However, the quadratic complexity of the self-attention mechanism in Transformer makes it inefficient in handling long sequences. Many existing works explore to accelerate Transformers by…

Computation and Language · Computer Science 2021-09-03 Chuhan Wu , Fangzhao Wu , Tao Qi , Binxing Jiao , Daxin Jiang , Yongfeng Huang , Xing Xie

The objective of this work is to establish an upper bound for the almost sure convergence rate for a class of push-sum algorithms. The current work extends the methods and results of the authors on a similar low-complexity bound on push-sum…

Probability · Mathematics 2025-07-23 Balázs Gerencsér , Miklós Kornyik

The self-attention mechanism is the key to the success of transformers in recent Large Language Models (LLMs). However, the quadratic computational cost $O(n^2)$ in the input sequence length $n$ is a notorious obstacle for further…

Machine Learning · Computer Science 2024-10-17 Yingyu Liang , Heshan Liu , Zhenmei Shi , Zhao Song , Zhuoyan Xu , Junze Yin

We study the distribution of a fully connected neural network with random Gaussian weights and biases in which the hidden layer widths are proportional to a large constant $n$. Under mild assumptions on the non-linearity, we obtain…

Machine Learning · Computer Science 2024-06-18 Stefano Favaro , Boris Hanin , Domenico Marinucci , Ivan Nourdin , Giovanni Peccati
‹ Prev 1 3 4 5 6 7 10 Next ›