English
Related papers

Related papers: You Only Sample (Almost) Once: Linear Cost Self-At…

200 papers

Much of recent Deep Reinforcement Learning success is owed to the neural architecture's potential to learn and use effective internal representations of the world. While many current algorithms access a simulator to train with a large…

Artificial Intelligence · Computer Science 2022-02-03 Amir Ardalan Kalantari , Mohammad Amini , Sarath Chandar , Doina Precup

Scaling Transformers to ultra-long contexts is bottlenecked by the $O(n^2 d)$ cost of self-attention. Existing methods reduce this cost along the sequence axis through local windows, kernel approximations, or token-level sparsity, but these…

Machine Learning · Computer Science 2026-03-31 Yan Xie , Tiansheng Wen , Tangda Huang , Bo Chen , Chenyu You , Stefanie Jegelka , Yifei Wang

Large Language Models (LLMs) face efficiency bottlenecks due to the quadratic complexity of the attention mechanism when processing long contexts. Sparse attention methods offer a promising solution, but existing approaches often suffer…

Computation and Language · Computer Science 2025-03-06 Lida Chen , Dong Xu , Chenxin An , Xintao Wang , Yikai Zhang , Jiangjie Chen , Zujie Liang , Feng Wei , Jiaqing Liang , Yanghua Xiao , Wei Wang

Transformer architectures deliver state-of-the-art accuracy via dense full-attention, but their quadratic time and memory complexity with respect to sequence length limits practical deployment. Linear attention mechanisms offer linear or…

Machine Learning · Computer Science 2026-01-21 Xiaojie Xia , Huigang Zhang , Chaoliang Zhong , Jun Sun , Yusuke Oishi

Transformers have shown dominant performance across a range of domains including language and vision. However, their computational cost grows quadratically with the sequence length, making their usage prohibitive for resource-constrained…

Computation and Language · Computer Science 2023-10-24 Yinghan Long , Sayeed Shafayet Chowdhury , Kaushik Roy

Transformer models cannot easily scale to long sequences due to their O(N^2) time and space complexity. This has led to Transformer variants seeking to lower computational complexity, such as Longformer and Performer. While such models have…

Computation and Language · Computer Science 2024-12-10 Guanghui Qin , Yukun Feng , Benjamin Van Durme

In this paper, to remedy this deficiency, we propose a Linear Attention Mechanism which is approximate to dot-product attention with much less memory and computational costs. The efficient design makes the incorporation between attention…

Computer Vision and Pattern Recognition · Computer Science 2020-08-21 Rui Li , Jianlin Su , Chenxi Duan , Shunyi Zheng

The dot product self-attention is known to be central and indispensable to state-of-the-art Transformer models. But is it really required? This paper investigates the true importance and contribution of the dot product-based self-attention…

Computation and Language · Computer Science 2021-05-25 Yi Tay , Dara Bahri , Donald Metzler , Da-Cheng Juan , Zhe Zhao , Che Zheng

Transformers achieve remarkable performance in several tasks but due to their quadratic complexity, with respect to the input's length, they are prohibitively slow for very long sequences. To address this limitation, we express the…

Machine Learning · Computer Science 2020-09-01 Angelos Katharopoulos , Apoorv Vyas , Nikolaos Pappas , François Fleuret

Linearization of attention using various kernel approximation and kernel learning techniques has shown promise. Past methods used a subset of combinations of component functions and weight matrices within the random feature paradigm. We…

Machine Learning · Computer Science 2025-09-24 Duke Nguyen , Du Yin , Aditya Joshi , Flora Salim

One limitation of existing Transformer-based models is that they cannot handle very long sequences as input since their self-attention operations exhibit quadratic time and space complexity. This problem becomes especially acute when…

Machine Learning · Computer Science 2024-05-07 Yuzhen Mao , Martin Ester , Ke Li

Since the Transformer architecture was introduced in 2017 there has been many attempts to bring the self-attention paradigm in the field of computer vision. In this paper we propose a novel self-attention module that can be easily…

Computer Vision and Pattern Recognition · Computer Science 2021-11-19 Roberto Pecoraro , Valerio Basile , Viviana Bono , Sara Gallo

The quadratic time and memory complexity inherent to self-attention mechanisms, with respect to sequence length, presents a critical computational bottleneck in the training and deployment of large-scale Transformer-based language models.…

Machine Learning · Computer Science 2024-03-19 Praneeth Kacham , Vahab Mirrokni , Peilin Zhong

Extensive efforts have been made to boost the performance in the domain of language models by introducing various attention-based transformers. However, the inclusion of linear layers with large dimensions contributes to significant…

Machine Learning · Computer Science 2024-11-19 Priyansh Bhatnagar , Linfeng Wen , Mingu Kang

Scaling the context length of large language models (LLMs) offers significant benefits but is computationally expensive. This expense stems primarily from the self-attention mechanism, whose $O(N^2)$ complexity with respect to sequence…

Computation and Language · Computer Science 2026-05-25 Xinghao Wang , Pengyu Wang , Dong Zhang , Chenkun Tan , Shaojun Zhou , Zhaoxiang Liu , Shiguo Lian , Fangxu Liu , Kai Song , Xipeng Qiu

Transformers have demonstrated a competitive performance across a wide range of vision tasks, while it is very expensive to compute the global self-attention. Many methods limit the range of attention within a local window to reduce…

Computer Vision and Pattern Recognition · Computer Science 2022-11-01 Zhenzhe Hechen , Wei Huang , Yixin Zhao

The emergence of spontaneous symmetry breaking among a few heads of multi-head attention (MHA) across transformer blocks in classification tasks was recently demonstrated through the quantification of single-nodal performance (SNP). This…

Computer Vision and Pattern Recognition · Computer Science 2025-07-01 Ronit D. Gross , Tal Halevi , Ella Koresh , Yarden Tzach , Ido Kanter

Although dominant in natural language processing, transformer-based models remain challenged by the task of long-sequence processing, because the computational cost of self-attention operations in transformers swells quadratically with the…

Computation and Language · Computer Science 2024-07-08 Jiawen Xie , Pengyu Cheng , Xiao Liang , Yong Dai , Nan Du

The advent of Transformers marked a significant breakthrough in sequence modelling, providing a highly performant architecture capable of leveraging GPU parallelism. However, Transformers are computationally expensive at inference time,…

Machine Learning · Computer Science 2024-05-29 Leo Feng , Frederick Tung , Hossein Hajimirsadeghi , Mohamed Osama Ahmed , Yoshua Bengio , Greg Mori

Modern language models rely on the transformer architecture and attention mechanism to perform language understanding and text generation. In this work, we study learning a 1-layer self-attention model from a set of prompts and associated…

Machine Learning · Computer Science 2024-02-22 M. Emrullah Ildiz , Yixiao Huang , Yingcong Li , Ankit Singh Rawat , Samet Oymak