English
Related papers

Related papers: Rethinking Attention: Polynomial Alternatives to S…

200 papers

Attention is a key part of the transformer architecture. It is a sequence-to-sequence mapping that transforms each sequence element into a weighted sum of values. The weights are typically obtained as the softmax of dot products between…

Attention architectures are widely used; they recently gained renewed popularity with Transformers yielding a streak of state of the art results. Yet, the geometrical implications of softmax-attention remain largely unexplored. In this work…

Machine Learning · Computer Science 2020-05-20 Oliver Richter , Roger Wattenhofer

Transformer attention is typically implemented using softmax normalization, which enforces attention weights with unit sum normalization. While effective in many settings, this constraint can limit flexibility in controlling attention…

Computation and Language · Computer Science 2026-02-27 Jeongin Bae , Baeseong Park , Gunho Park , Minsub Kim , Joonhyung Lee , Junhee Yoo , Sunghyeon Woo , Jiwon Ryu , Se Jung Kwon , Dongsoo Lee

Large transformer models have achieved state-of-the-art results in numerous natural language processing tasks. Among the pivotal components of the transformer architecture, the attention mechanism plays a crucial role in capturing token…

Computation and Language · Computer Science 2026-03-16 Yichuan Deng , Zhao Song , Kaijun Yuan , Tianyi Zhou

Attention is a core component of transformer architecture, whether encoder-only, decoder-only, or encoder-decoder model. However, the standard softmax attention often produces noisy probability distribution, which can impair effective…

Computation and Language · Computer Science 2025-11-11 Dhananjay Ram , Wei Xia , Stefano Soatto

The softmax function is crucial in Transformer attention, which normalizes each row of the attention scores with summation to one, achieving superior performances over other alternative functions. However, the softmax function can face a…

Computation and Language · Computer Science 2025-02-26 Chuanyang Zheng , Yihang Gao , Guoxuan Chen , Han Shi , Jing Xiong , Xiaozhe Ren , Chao Huang , Xin Jiang , Zhenguo Li , Yu Li

We illustrate the detrimental effect, such as overconfident decisions, that exponential behavior can have in methods like classical LDA and logistic regression. We then show how polynomiality can remedy the situation. This, among others,…

Machine Learning · Computer Science 2022-03-25 Ziqi Wang , Marco Loog

Transformers often display an attention sink: probability mass concentrates on a fixed, content-agnostic position. Are sinks a byproduct of the optimization/training regime? Or are they sometimes functionally necessary in softmax…

Machine Learning · Computer Science 2026-04-20 Yuval Ran-Milo

Softmax is widely used in neural networks for multiclass classification, gate structure and attention mechanisms. The statistical assumption that the input is normal distributed supports the gradient stability of Softmax. However, when used…

Computer Vision and Pattern Recognition · Computer Science 2021-08-17 Shulun Wang , Bin Liu , Feng Liu

Large language models rely on attention mechanisms with a softmax activation. Yet the dominance of softmax over alternatives (e.g., component-wise or linear) remains poorly understood, and many theoretical works have focused on the…

Machine Learning · Computer Science 2026-02-27 O. Duranthon , P. Marion , C. Boyer , B. Loureiro , L. Zdeborová

We introduce Performers, Transformer architectures which can estimate regular (softmax) full-rank-attention Transformers with provable accuracy, but using only linear (as opposed to quadratic) space and time complexity, without relying on…

At the core of the popular Transformer architecture is the self-attention mechanism, which dynamically assigns softmax weights to each input token so that the model can focus on the most salient information. However, the softmax structure…

Machine Learning · Computer Science 2025-05-27 Fanqi Yan , Huy Nguyen , Pedram Akbarian , Nhat Ho , Alessandro Rinaldo

The maximum element of the vector output by the Softmax function approaches zero as the input vector size increases. Transformer-based language models rely on Softmax to compute attention scores, causing the attention distribution to…

Computation and Language · Computer Science 2025-02-03 Ken M. Nakanishi

Various forms of sparse attention have been explored to mitigate the quadratic computational and memory cost of the attention mechanism in transformers. We study sparse transformers not through a lens of efficiency but rather in terms of…

Machine Learning · Computer Science 2025-06-19 Parikshit Ram , Kenneth L. Clarkson , Tim Klinger , Shashanka Ubaru , Alexander G. Gray

This paper investigates the limitations of the normalization in attention mechanisms. We begin with a theoretical framework that enables the identification of the model's selective ability and the geometric separation involved in token…

Machine Learning · Computer Science 2025-10-21 Timur Mudarisov , Mikhail Burtsev , Tatiana Petrova , Radu State

The Transformer model architecture has become one of the most widely used in deep learning and the attention mechanism is at its core. The standard attention formulation uses a softmax operation applied to a scaled dot product between query…

Machine Learning · Computer Science 2026-04-02 Hariprasath Govindarajan , Per Sidén , Jacob Roll , Fredrik Lindsten

Since its introduction, softmax attention has become the backbone of modern transformer architectures due to its expressiveness and scalability across a wide range of tasks. However, the main drawback of softmax attention is the quadratic…

Machine Learning · Computer Science 2026-02-20 Gabriel Mongaras , Eric C. Larson

Understanding the fundamental mechanism behind the success of transformer networks is still an open problem in the deep learning literature. Although their remarkable performance has been mostly attributed to the self-attention mechanism,…

Machine Learning · Computer Science 2022-11-23 Tolga Ergen , Behnam Neyshabur , Harsh Mehta

We propose a simple modification to the conventional attention mechanism applied by Transformers: Instead of quantifying pairwise query-key similarity with scaled dot-products, we quantify it with the logarithms of scaled dot-products of…

Machine Learning · Computer Science 2024-04-30 Franz A. Heinsen

Motivated by the factorization inherent in the original fast multipole method and the improved fast Gauss transform we introduce a factorable form of attention that operates efficiently in high dimensions. This approach reduces the…

Machine Learning · Computer Science 2024-02-13 Armin Gerami , Monte Hoover , Pranav S. Dulepet , Ramani Duraiswami
‹ Prev 1 2 3 10 Next ›