English
Related papers

Related papers: Skyformer: Remodel Self-Attention with Gaussian Ke…

200 papers

Large transformer models have shown extraordinary success in achieving state-of-the-art results in many natural language processing applications. However, training and deploying these models can be prohibitively costly for long sequences,…

Machine Learning · Computer Science 2020-06-16 Sinong Wang , Belinda Z. Li , Madian Khabsa , Han Fang , Hao Ma

We propose a novel class of kernels to alleviate the high computational cost of large-scale nonparametric learning with kernel methods. The proposed kernel is defined based on a hierarchical partitioning of the underlying data domain, where…

Machine Learning · Computer Science 2017-08-15 Jie Chen , Haim Avron , Vikas Sindhwani

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

Kernel methods provide a principled approach to nonparametric learning. While their basic implementations scale poorly to large problems, recent advances showed that approximate solvers can efficiently handle massive datasets. A shortcoming…

Machine Learning · Computer Science 2022-01-19 Giacomo Meanti , Luigi Carratino , Ernesto De Vito , Lorenzo Rosasco

In many areas of machine learning, it becomes necessary to find the eigenvector decompositions of large matrices. We discuss two methods for reducing the computational burden of spectral decompositions: the more venerable Nystom extension…

Machine Learning · Statistics 2011-07-22 Darren Homrighausen , Daniel J. McDonald

Recent advances in Transformer architectures have empowered their empirical success in a variety of tasks across different domains. However, existing works mainly focus on predictive accuracy and computational cost, without considering…

Machine Learning · Computer Science 2023-11-09 Xing Han , Tongzheng Ren , Tan Minh Nguyen , Khai Nguyen , Joydeep Ghosh , Nhat Ho

Recently, a new line of works has emerged to understand and improve self-attention in Transformers by treating it as a kernel machine. However, existing works apply the methods for symmetric kernels to the asymmetric self-attention,…

Machine Learning · Computer Science 2023-12-06 Yingyi Chen , Qinghua Tao , Francesco Tonin , Johan A. K. Suykens

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

The success of self-attention (SA) in Transformer demonstrates the importance of non-local information to image super-resolution (SR), but the huge computing power required makes it difficult to implement lightweight models. To solve this…

Image and Video Processing · Electrical Eng. & Systems 2025-08-18 Yinggan Tang , Quanwei Hu

While Bayesian inference provides a principled framework for reasoning under uncertainty, its widespread adoption is limited by the intractability of exact posterior computation, necessitating the use of approximate inference. However,…

Machine Learning · Statistics 2026-05-19 George Whittle , Juliusz Ziomek , Jacob Rawling , Maike A. Osborne

We provide the first mathematically complete derivation of the Nystr\"om method for low-rank approximation of indefinite kernels and propose an efficient method for finding an approximate eigendecomposition of such kernel matrices. Building…

Machine Learning · Statistics 2019-06-03 Dino Oglic , Thomas Gärtner

The bilateral and nonlocal means filters are instances of kernel-based filters that are popularly used in image processing. It was recently shown that fast and accurate bilateral filtering of grayscale images can be performed using a…

Computer Vision and Pattern Recognition · Computer Science 2019-02-20 Pravin Nair , Kunal N. Chaudhury

In this thesis, we introduce Greenformers, a collection of model efficiency methods to improve the model efficiency of the recently renowned transformer models with a low-rank approximation approach. The development trend of deep learning…

Machine Learning · Computer Science 2021-08-25 Samuel Cahyawijaya

Support Vector Machines (SVMs) are among the most popular and the best performing classification algorithms. Various approaches have been proposed to reduce the high computation and memory cost when training and predicting based on…

Machine Learning · Computer Science 2020-07-24 Chen Jiang , Qingna Li

Previous works have shown that reducing parameter overhead and computations for transformer-based single image super-resolution (SISR) models (e.g., SwinIR) usually leads to a reduction of performance. In this paper, we present GRFormer, an…

Computer Vision and Pattern Recognition · Computer Science 2024-08-15 Yuzhen Li , Zehang Deng , Yuxin Cao , Lihua Liu

Kernel mean embeddings are a powerful tool to represent probability distributions over arbitrary spaces as single points in a Hilbert space. Yet, the cost of computing and storing such embeddings prohibits their direct use in large-scale…

Machine Learning · Statistics 2022-06-16 Antoine Chatalic , Nicolas Schreuder , Alessandro Rudi , Lorenzo Rosasco

Vision transformers (ViTs) have pushed the state-of-the-art for various visual recognition tasks by patch-wise image tokenization followed by self-attention. However, the employment of self-attention modules results in a quadratic…

Computer Vision and Pattern Recognition · Computer Science 2022-05-03 Jiachen Lu , Jinghan Yao , Junge Zhang , Xiatian Zhu , Hang Xu , Weiguo Gao , Chunjing Xu , Tao Xiang , Li Zhang

Autoregressive Transformers are strong language models but incur O(T) complexity during per-token generation due to the self-attention mechanism. Recent work proposes kernel-based methods to approximate causal self-attention by replacing it…

Machine Learning · Computer Science 2022-10-11 Huanru Henry Mao

Self-Attention Mechanisms (SAMs) enhance model performance by extracting key information but are inefficient when dealing with long sequences. To this end, a photonic Gaussian Kernel Enhanced Transformer (PGKET) is proposed, based on the…

Quantum Physics · Physics 2025-07-28 Ren-Xin Zhao

The attention mechanism is the computational core of modern Transformer architectures, but its quadratic complexity in the input sequence length is the bottleneck for large-scale inference. This has motivated a rapidly growing body of work…