English
Related papers

Related papers: Rethinking Attention: Polynomial Alternatives to S…

200 papers

Large language models have achieved remarkable success in recent years, primarily due to self-attention. However, traditional Softmax attention suffers from numerical instability and reduced performance as the number of inference tokens…

Computation and Language · Computer Science 2026-02-02 Bo Gao , Michael W. Spratling , Letizia Gionfrida

The adversarial robustness of attributions is a fundamental requirement for reliable explainability in deep learning, yet existing approaches typically rely on computationally expensive explicit regularization. In this work, we show that…

Machine Learning · Computer Science 2026-05-29 Amir Mehrpanah , Matteo Gamba , Hossein Azizpour

Softmax is popular normalization method used in machine learning. Deep learning solutions like Transformer or BERT use the softmax function intensively, so it is worthwhile to optimize its performance. This article presents our methodology…

Mathematical Software · Computer Science 2019-05-28 Jacek Czaja , Michal Gallus , Tomasz Patejko , Jian Tang

Transformers have had tremendous impact for several sequence related tasks, largely due to their ability to retrieve from any part of the sequence via softmax based dot-product attention. This mechanism plays a crucial role in Transformer's…

Machine Learning · Computer Science 2025-07-15 Sai Surya Duvvuri , Inderjit S. Dhillon

Understanding the intricate non-convex training dynamics of softmax-based models is crucial for explaining the empirical success of transformers. In this article, we analyze the gradient flow dynamics of the value-softmax model, defined as…

Machine Learning · Computer Science 2026-03-09 Aditya Varre , Mark Rofin , Nicolas Flammarion

Transformers are state-of-the-art models for a variety of sequence modeling tasks. At their core is an attention function which models pairwise interactions between the inputs at every timestep. While attention is powerful, it does not…

Computation and Language · Computer Science 2021-03-23 Hao Peng , Nikolaos Pappas , Dani Yogatama , Roy Schwartz , Noah A. Smith , Lingpeng Kong

Central to the success of Transformers is the attention block, which effectively models global dependencies among input tokens associated to a dataset. However, we theoretically demonstrate that standard attention mechanisms in transformers…

Machine Learning · Computer Science 2026-03-31 Hemanth Saratchandran

We study conditions under which transformers using soft attention can simulate hard attention, that is, effectively focus all attention on a subset of positions. First, we examine several subclasses of languages recognized by hard-attention…

Machine Learning · Computer Science 2025-06-27 Andy Yang , Lena Strobl , David Chiang , Dana Angluin

The original softmax-based attention mechanism (regular attention) in the extremely successful Transformer architecture computes attention between $N$ tokens, each embedded in a $D$-dimensional head, with a time complexity of $O(N^2D)$.…

Machine Learning · Computer Science 2025-10-28 Armin Gerami , Ramani Duraiswami

The softmax function is widely used in artificial neural networks for the multiclass classification problems, where the softmax transformation enforces the output to be positive and sum to one, and the corresponding loss function allows to…

Machine Learning · Computer Science 2021-12-24 Shaoshi Sun , Zhenyuan Zhang , BoCheng Huang , Pengbin Lei , Jianlin Su , Shengfeng Pan , Jiarun Cao

Transformers are mostly relying on softmax attention, which introduces quadratic complexity with respect to sequence length and remains a major bottleneck for efficient inference. Prior work on linear or hybrid attention typically replaces…

Previous research observed accuracy degradation when replacing the attention softmax with a point-wise activation such as ReLU. In the context of vision transformers, we find that this degradation is mitigated when dividing by sequence…

Computer Vision and Pattern Recognition · Computer Science 2023-10-18 Mitchell Wortsman , Jaehoon Lee , Justin Gilmer , Simon Kornblith

Attention mechanisms, particularly softmax attention, have been instrumental in the success of transformer-based models such as GPT. However, the quadratic memory complexity of softmax attention with respect to sequence length poses…

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

To enhance the computational efficiency of quantized Transformers, we replace the dot-product and Softmax-based attention with an alternative mechanism involving addition and ReLU activation only. This side-steps the expansion to double…

Machine Learning · Computer Science 2025-10-02 Rickard Brännvall , Andrei Stoian

Modern neural networks are often augmented with an attention mechanism, which tells the network where to focus within the input. We propose in this paper a new framework for sparse and structured attention, building upon a smoothed max…

Machine Learning · Statistics 2019-02-26 Vlad Niculae , Mathieu Blondel

Recently, it has been argued that encoder-decoder models can be made more interpretable by replacing the softmax function in the attention with its sparse variants. In this work, we introduce a novel, simple method for achieving sparsity in…

Computation and Language · Computer Science 2021-10-07 Biao Zhang , Ivan Titov , Rico Sennrich

Non-local (NL) block is a popular module that demonstrates the capability to model global contexts. However, NL block generally has heavy computation and memory costs, so it is impractical to apply the block to high-resolution feature maps.…

Computer Vision and Pattern Recognition · Computer Science 2022-07-28 Yooshin Cho , Youngsoo Kim , Hanbyel Cho , Jaesung Ahn , Hyeong Gwon Hong , Junmo Kim

Softmax-based dot-product attention is a cornerstone of Transformer architectures, enabling remarkable capabilities such as in-context learning. However, as context lengths increase, a fundamental limitation of the softmax function emerges:…

Machine Learning · Computer Science 2026-02-12 Sai Surya Duvvuri , Nirmal Patel , Nilesh Gupta , Inderjit S. Dhillon

The quadratic complexity of softmax attention presents a major obstacle for scaling Transformers to high-resolution vision tasks. Existing linear attention variants often replace the softmax with Gaussian kernels to reduce complexity, but…

Computer Vision and Pattern Recognition · Computer Science 2026-04-23 Zhe Feng , Sen Lian , Changwei Wang , Muyang Zhang , Tianlong Tan , Rongtao Xu , Weiliang Meng , Xiaopeng Zhang

Linear attention has emerged as a promising alternative to softmax-based attention, leveraging kernelized feature maps to reduce complexity from quadratic to linear in sequence length. However, the non-negative constraint on feature maps…

Computer Vision and Pattern Recognition · Computer Science 2025-03-05 Weikang Meng , Yadan Luo , Xin Li , Dongmei Jiang , Zheng Zhang