English
Related papers

Related papers: Rethinking Attention: Polynomial Alternatives to S…

200 papers

While linear attention reduces the quadratic complexity of standard Transformers to linear time, it often lags behind in expressivity due to the removal of softmax normalization. This omission eliminates \emph{global competition}, a…

Machine Learning · Computer Science 2026-02-03 Mingwei Xu , Xuan Lin , Xinnan Guo , Wanqing Xu , Wanyun Cui

The self-attention mechanism, at the heart of the Transformer model, is able to effectively model pairwise interactions between tokens. However, numerous recent works have shown that it is unable to perform basic tasks involving detecting…

Machine Learning · Computer Science 2026-02-03 Sayak Chakrabarti , Toniann Pitassi , Josh Alman

Softmax is widely used in deep learning to map some representation to a probability distribution. As it is based on exp/log functions that are relatively expensive in multi-party computation, Mohassel and Zhang (2017) proposed a simpler…

Machine Learning · Computer Science 2021-07-07 Marcel Keller , Ke Sun

Normalization techniques are crucial for enhancing Transformer models' performance and stability in time series analysis tasks, yet traditional methods like batch and layer normalization often lead to issues such as token shift, attention…

Machine Learning · Computer Science 2024-05-28 Nan Huang , Christian Kümmerle , Xiang Zhang

The attention module is the key component in Transformers. While the global attention mechanism offers high expressiveness, its excessive computational cost restricts its applicability in various scenarios. In this paper, we propose a novel…

Computer Vision and Pattern Recognition · Computer Science 2024-07-16 Dongchen Han , Tianzhu Ye , Yizeng Han , Zhuofan Xia , Siyuan Pan , Pengfei Wan , Shiji Song , Gao Huang

We provide a systematic recipe for translating ReLU approximation results to softmax attention mechanism. This recipe covers many common approximation targets. Importantly, it yields target-specific, economic resource bounds beyond…

Machine Learning · Computer Science 2026-04-29 Jerry Yao-Chieh Hu , Mingcheng Lu , Yi-Chen Lee , Han Liu

The self-attention mechanism traditionally relies on the softmax operator, necessitating positional embeddings like RoPE, or position biases to account for token order. But current methods using still face length generalisation challenges.…

Machine Learning · Computer Science 2025-05-21 Shawn Tan , Songlin Yang , Aaron Courville , Rameswar Panda , Yikang Shen

Transformer architectures have achieved remarkable empirical success in modeling contextual relations, yet a clear understanding of their expressive power is still lacking. In this work, we introduce a measure-theoretic framework in which…

Machine Learning · Statistics 2026-05-19 Demián Fraiman

The Transformer architecture consists of self-attention and feed-forward networks (FFNs) which can be viewed as key-value memories according to previous works. However, FFN and traditional memory utilize different activation functions…

Computation and Language · Computer Science 2023-02-14 Kai Shen , Junliang Guo , Xu Tan , Siliang Tang , Rui Wang , Jiang Bian

Transformers are increasingly adopted for modeling and forecasting time-series, yet their internal mechanisms remain poorly understood from a dynamical systems perspective. In contrast to classical autoregressive and state-space models,…

Machine Learning · Computer Science 2025-12-25 Gregory Duthé , Nikolaos Evangelou , Wei Liu , Ioannis G. Kevrekidis , Eleni Chatzi

We present a theoretical analysis of the performance of transformer with softmax attention in in-context learning with linear regression tasks. While the existing literature predominantly focuses on the convergence of transformers with…

Machine Learning · Computer Science 2024-02-01 Yingqian Cui , Jie Ren , Pengfei He , Jiliang Tang , Yue Xing

A key property of reasoning systems is the ability to make sharp decisions on their input data. For contemporary AI systems, a key carrier of sharp behaviour is the softmax function, with its capability to perform differentiable query-key…

Machine Learning · Computer Science 2025-06-03 Petar Veličković , Christos Perivolaropoulos , Federico Barbero , Razvan Pascanu

Transformers have revolutionized deep learning in numerous fields, including natural language processing, computer vision, and audio processing. Their strength lies in their attention mechanism, which allows for the discovering of complex…

Machine Learning · Computer Science 2024-04-02 Uladzislau Yorsh , Martin Holeňa , Ondřej Bojar , David Herel

While attention has been empirically shown to improve model performance, it lacks a rigorous mathematical justification. This short paper establishes a novel connection between attention mechanisms and multinomial regression. Specifically,…

Machine Learning · Computer Science 2025-10-28 Jonas A. Actor , Anthony Gruber , Eric C. Cyr

An essential component of modern recurrent sequence models is the forget gate. While Transformers do not have an explicit recurrent form, we show that a forget gate can be naturally incorporated into Transformers by down-weighting the…

Machine Learning · Computer Science 2025-04-02 Zhixuan Lin , Evgenii Nikishin , Xu Owen He , Aaron Courville

We prove that with linear transformations, both (i) two-layer self-attention and (ii) one-layer self-attention followed by a softmax function are universal approximators for continuous sequence-to-sequence functions on compact domains. Our…

Machine Learning · Computer Science 2025-12-17 Jerry Yao-Chieh Hu , Hude Liu , Hong-Yu Chen , Weimin Wu , Han Liu

We propose a novel attention mechanism, named Cog Attention, that enables attention weights to be negative for enhanced expressiveness, which stems from two key factors: (1) Cog Attention enhances parameter flexibility. For example, unlike…

Computation and Language · Computer Science 2025-01-31 Ang Lv , Ruobing Xie , Shuaipeng Li , Jiayi Liao , Xingwu Sun , Zhanhui Kang , Di Wang , Rui Yan

Linear attentions have shown potential for improving Transformer efficiency, reducing attention's quadratic complexity to linear in sequence length. This holds exciting promise for (1) training linear Transformers from scratch, (2)…

Machine Learning · Computer Science 2024-02-08 Michael Zhang , Kush Bhatia , Hermann Kumbong , Christopher Ré

At the core of the Transformer, the softmax normalizes the attention matrix to be right stochastic. Previous research has shown that this often de-stabilizes training and that enforcing the attention matrix to be doubly stochastic (through…

Machine Learning · Computer Science 2025-11-11 Jannis Born , Filip Skogh , Kahn Rhrissorrakrai , Filippo Utro , Nico Wagner , Aleksandros Sobczyk

There is a growing interest in the ability of neural networks to execute algorithmic tasks (e.g., arithmetic, summary statistics, and sorting). The goal of this work is to better understand the role of attention in Transformers for…

Machine Learning · Computer Science 2025-06-11 Artur Back de Luca , George Giapitzakis , Shenghao Yang , Petar Veličković , Kimon Fountoulakis