English
Related papers

Related papers: Rethinking Attention: Polynomial Alternatives to S…

200 papers

Converting an n-dimensional vector to a probability distribution over n objects is a commonly used component in many machine learning tasks like multiclass classification, multilabel classification, attention mechanisms etc. For this,…

Despite powering modern AI, transformers remain mysteriously brittle to train. We develop a stability theory that explains why pre-LayerNorm works, why DeepNorm uses $N^{-1/4}$ scaling, and why warmup is necessary, all from first…

Machine Learning · Computer Science 2026-02-24 Seyed Morteza Emadi

The attention mechanism is a pivotal element within the transformer architecture, making a substantial contribution to its exceptional performance. Within this attention mechanism, Softmax is an imperative component that enables the model…

Hardware Architecture · Computer Science 2024-09-05 Tianhua Xia , Sai Qian Zhang

Transformers have achieved state-of-the-art performance across various tasks, but suffer from a notable quadratic complexity in sequence length due to the attention mechanism. In this work, we propose MonarchAttention -- a novel approach to…

Machine Learning · Computer Science 2025-10-28 Can Yaras , Alec S. Xu , Pierre Abillama , Changwoo Lee , Laura Balzano

To improve the robustness of transformer neural networks used for temporal-dynamics prediction of chaotic systems, we propose a novel attention mechanism called easy attention which we demonstrate in time-series reconstruction and…

Machine Learning · Computer Science 2025-06-05 Marcial Sanchis-Agudo , Yuning Wang , Roger Arnau , Luca Guastoni , Jasmin Lim , Karthik Duraisamy , Ricardo Vinuesa

Transformers have achieved remarkable successes across a wide range of applications, yet the theoretical foundation of their model efficiency remains underexplored. In this work, we investigate how the model parameters -- mainly attention…

Machine Learning · Computer Science 2025-10-07 Ruoxi Yu , Haotian Jiang , Jingpu Cheng , Penghao Yu , Qianxiao Li , Zhong Li

The Transformer model has been pivotal in advancing fields such as natural language processing, speech recognition, and computer vision. However, a critical limitation of this model is its quadratic computational and memory complexity…

Computer Vision and Pattern Recognition · Computer Science 2024-06-04 Firas Khader , Omar S. M. El Nahhas , Tianyu Han , Gustav Müller-Franzes , Sven Nebelung , Jakob Nikolas Kather , Daniel Truhn

We study two strange phenomena in auto-regressive Transformers: (1) the dominance of the first token in attention heads; (2) the occurrence of large outlier activations in the hidden states. We find that popular large language models, such…

Computation and Language · Computer Science 2024-10-23 Prannay Kaul , Chengcheng Ma , Ismail Elezi , Jiankang Deng

Transformers are widely used across various applications, many of which yield sparse or partially filled attention matrices. Examples include attention masks designed to reduce the quadratic complexity of attention, sequence packing…

Machine Learning · Computer Science 2024-09-25 Agniv Sharma , Jonas Geiping

Various linear complexity models, such as Linear Transformer (LinFormer), State Space Model (SSM), and Linear RNN (LinRNN), have been proposed to replace the conventional softmax attention in Transformer structures. However, the optimal…

Machine Learning · Computer Science 2024-11-19 Yuhong Chou , Man Yao , Kexin Wang , Yuqi Pan , Ruijie Zhu , Yiran Zhong , Yu Qiao , Jibin Wu , Bo Xu , Guoqi Li

We introduce a new discrete-time attention model, termed the localmax dynamics, which interpolates between the classic softmax dynamics and the hardmax dynamics, where only the tokens that maximize the influence toward a given token have a…

Computation and Language · Computer Science 2025-09-22 Henri Cimetière , Maria Teresa Chiri , Bahman Gharesifard

Vision Transformers have achieved impressive performance in video classification, while suffering from the quadratic complexity caused by the Softmax attention mechanism. Some studies alleviate the computational costs by reducing the number…

Computer Vision and Pattern Recognition · Computer Science 2022-10-18 Kaiyue Lu , Zexiang Liu , Jianyuan Wang , Weixuan Sun , Zhen Qin , Dong Li , Xuyang Shen , Hui Deng , Xiaodong Han , Yuchao Dai , Yiran Zhong

Exponential families are widely used in machine learning; they include many distributions in continuous and discrete domains (e.g., Gaussian, Dirichlet, Poisson, and categorical distributions via the softmax transformation). Distributions…

Neural networks utilize the softmax as a building block in classification tasks, which contains an overconfidence problem and lacks an uncertainty representation ability. As a Bayesian alternative to the softmax, we consider a random…

Machine Learning · Computer Science 2020-06-30 Taejong Joo , Uijung Chung , Min-Gwan Seo

Attention mechanism is contributing to the majority of recent advances in machine learning for natural language processing. Additionally, it results in an attention map that shows the proportional influence of each input in its decision.…

Computation and Language · Computer Science 2025-01-23 Duc Hau Nguyen , Cyrielle Mallart , Guillaume Gravier , Pascale Sébillot

We study transformer language models, analyzing attention heads whose attention patterns are spread out, and whose attention scores depend weakly on content. We argue that the softmax denominators of these heads are stable when the…

Computation and Language · Computer Science 2025-10-07 Alex Gibson

The softmax activation function plays a crucial role in the success of large language models (LLMs), particularly in the self-attention mechanism of the widely adopted Transformer architecture. However, the underlying learning dynamics that…

Machine Learning · Computer Science 2026-01-27 Yang Cao , Yingyu Liang , Zhenmei Shi , Zhao Song

We examine the intrinsic (within the attention head) and extrinsic (amongst the attention heads) structure of the self-attention mechanism in transformers. Theoretical evidence for invariance of the self-attention mechanism to softmax…

Numerical Analysis · Mathematics 2025-06-19 Oluwadamilola Fasina , Ruben V. C. Pohle , Pei-Chun Su , Ronald R. Coifman

In deep learning theory, the covariance matrix of the representations serves as a proxy to examine the network's trainability. Motivated by the success of Transformers, we study the covariance matrix of a modified Softmax-based attention…

Machine Learning · Statistics 2023-12-12 Lorenzo Noci , Chuning Li , Mufan Bill Li , Bobby He , Thomas Hofmann , Chris Maddison , Daniel M. Roy

We study how multi-head softmax attention models are trained to perform in-context learning on linear data. Through extensive empirical experiments and rigorous theoretical analysis, we demystify the emergence of elegant attention patterns:…

Machine Learning · Computer Science 2025-05-29 Jianliang He , Xintian Pan , Siyu Chen , Zhuoran Yang
‹ Prev 1 3 4 5 6 7 10 Next ›