English
Related papers

Related papers: On Learning the Transformer Kernel

200 papers

Recent works on parameter-efficient transfer learning (PETL) show the potential to adapt a pre-trained Vision Transformer to downstream recognition tasks with only a few learnable parameters. However, since they usually insert new…

Computer Vision and Pattern Recognition · Computer Science 2024-07-16 Taolin Zhang , Jiawang Bai , Zhihe Lu , Dongze Lian , Genping Wang , Xinchao Wang , Shu-Tao Xia

Kernel matrices are crucial in many learning tasks such as support vector machines or kernel ridge regression. The kernel matrix is typically dense and large-scale. Depending on the dimension of the feature space even the computation of all…

Machine Learning · Computer Science 2023-12-04 Franziska Nestler , Martin Stoll , Theresa Wagner

How can neural networks such as ResNet efficiently learn CIFAR-10 with test accuracy more than 96%, while other methods, especially kernel methods, fall relatively behind? Can we more provide theoretical justifications for this gap?…

Machine Learning · Computer Science 2020-06-02 Zeyuan Allen-Zhu , Yuanzhi Li

For the past 30 years or so, machine learning has stimulated a great deal of research in the study of approximation capabilities (expressive power) of a multitude of processes, such as approximation by shallow or deep neural networks,…

Machine Learning · Computer Science 2025-01-07 Hrushikesh Mhaskar

Large kernel convolutions offer a scalable alternative to vision transformers for high-resolution 3D volumetric analysis, yet naively increasing kernel size often leads to optimization instability. Motivated by the spatial bias inherent in…

Computer Vision and Pattern Recognition · Computer Science 2026-02-02 Ho Hin Lee , Quan Liu , Shunxing Bao , Yuankai Huo , Bennett A. Landman

In this paper we derive an efficient algorithm to learn the parameters of structured predictors in general graphical models. This algorithm blends the learning and inference tasks, which results in a significant speedup over traditional…

Machine Learning · Computer Science 2013-09-02 Tamir Hazan , Alexander Schwing , David McAllester , Raquel Urtasun

The computational complexity of kernel methods has often been a major barrier for applying them to large-scale learning problems. We argue that this barrier can be effectively overcome. In particular, we develop methods to scale up kernel…

Tabular foundation models like TabPFN and TabICL achieve state-of-the-art performance through in-context learning, yet their architectures remain fundamentally opaque. We introduce KernelICL, a framework to enhance tabular foundation models…

Machine Learning · Computer Science 2026-02-03 Ratmir Miftachov , Bruno Charron , Simon Valentin

Data similarity is a key concept in many data-driven applications. Many algorithms are sensitive to similarity measures. To tackle this fundamental problem, automatically learning of similarity information from data via self-expression has…

Machine Learning · Computer Science 2019-03-12 Zhao Kang , Yiwei Lu , Yuanzhang Su , Changsheng Li , Zenglin Xu

Quantum kernel method is one of the key approaches to quantum machine learning, which has the advantages that it does not require optimization and has theoretical simplicity. By virtue of these properties, several experimental…

Quantum Physics · Physics 2022-11-28 Norihito Shirai , Kenji Kubo , Kosuke Mitarai , Keisuke Fujii

Transformers have become the dominant architecture for sequence modeling tasks such as natural language processing or audio processing, and they are now even considered for tasks that are not naturally sequential such as image…

Machine Learning · Computer Science 2024-03-05 Jorg Bornschein , Yazhe Li , Amal Rannen-Triki

We consider the task of building compact deep learning pipelines suitable for deployment on storage and power constrained mobile devices. We propose a unified framework to learn a broad family of structured parameter matrices that are…

Machine Learning · Statistics 2015-10-07 Vikas Sindhwani , Tara N. Sainath , Sanjiv Kumar

As the rapidly evolving field of machine learning continues to produce incredibly useful tools and models, the potential for quantum computing to provide speed up for machine learning algorithms is becoming increasingly desirable. In…

Quantum Physics · Physics 2024-04-02 Anthony M. Smaldone , Gregory W. Kyro , Victor S. Batista

The Transformer-Kernel (TK) model has demonstrated strong reranking performance on the TREC Deep Learning benchmark -- and can be considered to be an efficient (but slightly less effective) alternative to other Transformer-based…

Information Retrieval · Computer Science 2021-04-20 Bhaskar Mitra , Sebastian Hofstatter , Hamed Zamani , Nick Craswell

Modern deep neural networks require a tremendous amount of data to train, often needing hundreds or thousands of labeled examples to learn an effective representation. For these networks to work with less data, more structure must be built…

Computer Vision and Pattern Recognition · Computer Science 2019-03-06 Reuben Feinman , Brenden M. Lake

A well-recognized limitation of kernel learning is the requirement to handle a kernel matrix, whose size is quadratic in the number of training examples. Many methods have been proposed to reduce this computational cost, mostly by using a…

Machine Learning · Computer Science 2014-11-06 Nicolò Cesa-Bianchi , Yishay Mansour , Ohad Shamir

In deep learning models, learning more with less data is becoming more important. This paper explores how neural networks with normalized Radial Basis Function (RBF) kernels can be trained to achieve better sample efficiency. Moreover, we…

Various Graph Neural Networks (GNNs) have been successful in analyzing data in non-Euclidean spaces, however, they have limitations such as oversmoothing, i.e., information becomes excessively averaged as the number of hidden layers…

Machine Learning · Computer Science 2024-01-23 Jaeyoon Sim , Sooyeon Jeon , InJun Choi , Guorong Wu , Won Hwa Kim

Time series forecasting task predicts future trends based on historical information. Transformer-based U-Net architectures, despite their success in medical image segmentation, have limitations in both expressiveness and computation…

Machine Learning · Computer Science 2024-09-10 Jiang You , Arben Cela , René Natowicz , Jacob Ouanounou , Patrick Siarry

We propose and analyze a kernelized version of Q-learning. Although a kernel space is typically infinite-dimensional, extensive study has shown that generalization is only affected by the effective dimension of the data. We incorporate such…

Machine Learning · Computer Science 2022-04-25 Shuang Liu , Hao Su