English
Related papers

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

200 papers

Transformer is a powerful tool for many natural language tasks which is based on self-attention, a mechanism that encodes the dependence of other tokens on each specific token, but the computation of self-attention is a bottleneck due to…

Machine Learning · Computer Science 2021-03-11 Madhusudan Verma

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

Kernel methods are a popular class of nonlinear predictive models in machine learning. Scalable algorithms for learning kernel models need to be iterative in nature, but convergence can be slow due to poor conditioning. Spectral…

Machine Learning · Statistics 2024-01-26 Amirhesam Abedsoltan , Parthe Pandit , Luis Rademacher , Mikhail Belkin

Many kernel methods suffer from high time and space complexities and are thus prohibitive in big-data applications. To tackle the computational challenge, the Nystr\"om method has been extensively used to reduce time and space complexities…

Machine Learning · Computer Science 2014-04-02 Shusen Wang , Zhihua Zhang

Kernel-based models such as kernel ridge regression and Gaussian processes are ubiquitous in machine learning applications for regression and optimization. It is well known that a major downside for kernel-based models is the high…

Machine Learning · Computer Science 2022-06-22 Sattar Vakili , Jonathan Scarlett , Da-shan Shiu , Alberto Bernacchia

Transformers have emerged as a powerful tool for a broad range of natural language processing tasks. A key component that drives the impressive performance of Transformers is the self-attention mechanism that encodes the influence or…

Computation and Language · Computer Science 2021-04-02 Yunyang Xiong , Zhanpeng Zeng , Rudrasis Chakraborty , Mingxing Tan , Glenn Fung , Yin Li , Vikas Singh

The problem of efficient approximation of a linear operator induced by the Gaussian or softmax kernel is often addressed using random features (RFs) which yield an unbiased approximation of the operator's result. Such operators emerge in…

Machine Learning · Computer Science 2023-02-03 Valerii Likhosherstov , Krzysztof Choromanski , Avinava Dubey , Frederick Liu , Tamas Sarlos , Adrian Weller

Symmetric positive semi-definite (SPSD) matrix approximation methods have been extensively used to speed up large-scale eigenvalue computation and kernel learning methods. The standard sketch based method, which we call the prototype model,…

Machine Learning · Computer Science 2016-12-13 Shusen Wang , Zhihua Zhang , Tong Zhang

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

Kernel machines have sustained continuous progress in the field of quantum chemistry. In particular, they have proven to be successful in the low-data regime of force field reconstruction. This is because many equivariances and invariances…

Chemical Physics · Physics 2023-07-12 Stefan Blücher , Klaus-Robert Müller , Stefan Chmiela

Transformers excel across domains, yet their quadratic attention complexity poses a barrier to scaling. Random-feature attention, as in Performers, can reduce this cost to linear in the sequence length by approximating the softmax kernel…

Machine Learning · Computer Science 2026-03-05 Amirhossein Farzam , Hossein Mobahi , Nolan Andrew Miller , Luke Sernau

Self-attention in Transformers is typically implemented as $\mathrm{softmax}(QK^\top/\sqrt{d})V$, where $Q=XW_Q$, $K=XW_K$, and $V=XW_V$ are learned linear projections of the input $X$. We ask whether these learned projections are…

Machine Learning · Computer Science 2026-05-05 Debarshi Kundu , Archisman Ghosh , Swaroop Ghosh , Vasant Honavar

When implementations of the Transformer's self-attention layer utilize SRAM instead of DRAM, they can achieve significant speedups. The Tenstorrent Grayskull architecture provides a large SRAM, distributed across a grid of cores. This work…

Machine Learning · Computer Science 2024-07-22 Moritz Thüning

In pursuit of faster computation, Efficient Transformers demonstrate an impressive variety of approaches -- models attaining sub-quadratic attention complexity can utilize a notion of sparsity or a low-rank approximation of inputs to reduce…

Machine Learning · Computer Science 2022-11-09 Uladzislau Yorsh , Alexander Kovalenko

Transformer has shown great successes in natural language processing, computer vision, and audio processing. As one of its core components, the softmax attention helps to capture long-range dependencies yet prohibits its scale-up due to the…

Computation and Language · Computer Science 2022-02-18 Zhen Qin , Weixuan Sun , Hui Deng , Dongxu Li , Yunshen Wei , Baohong Lv , Junjie Yan , Lingpeng Kong , Yiran Zhong

We propose a new technique for constructing low-rank approximations of matrices that arise in kernel methods for machine learning. Our approach pairs a novel automatically constructed analytic expansion of the underlying kernel function…

Machine Learning · Computer Science 2022-02-09 John Paul Ryan , Anil Damle

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

Kernel methods offer the flexibility to learn complex relationships in modern, large data sets while enjoying strong theoretical guarantees on quality. Unfortunately, these methods typically require cubic running time in the data set size,…

Machine Learning · Statistics 2019-03-01 Raj Agrawal , Trevor Campbell , Jonathan H. Huggins , Tamara Broderick

The Nystr\"om methods have been popular techniques for scalable kernel based learning. They approximate explicit, low-dimensional feature mappings for kernel functions from the pairwise comparisons with the training data. However, Nystr\"om…

Machine Learning · Computer Science 2018-05-21 Mert Al , Thee Chanyaswad , Sun-Yuan Kung

The Nystrom method is a popular technique that uses a small number of landmark points to compute a fixed-rank approximation of large kernel matrices that arise in machine learning problems. In practice, to ensure high quality…

Machine Learning · Statistics 2019-12-04 Farhad Pourkamali-Anaraki , Stephen Becker
‹ Prev 1 2 3 10 Next ›