中文
相关论文

相关论文: On the validity of kernel approximations for ortho…

200 篇论文

Kernel ridge regression (KRR) is a standard method for performing non-parametric regression over reproducing kernel Hilbert spaces. Given $n$ samples, the time and space complexity of computing the KRR estimate scale as $\mathcal{O}(n^3)$…

机器学习 · 统计学 2015-01-27 Yun Yang , Mert Pilanci , Martin J. Wainwright

Neural tangent kernels (NTKs) have been proposed to study the behavior of trained neural networks from the perspective of Gaussian processes. An important result in this body of work is the theorem of equivalence between a trained neural…

机器学习 · 统计学 2025-01-22 Haoran Liu , Anthony Tai , David J. Crandall , Chunfeng Huang

We explore the equivalence between neural networks and kernel methods by deriving the first exact representation of any finite-size parametric classification model trained with gradient descent as a kernel machine. We compare our exact…

机器学习 · 计算机科学 2023-08-10 Brian Bell , Michael Geyer , David Glickenstein , Amanda Fernandez , Juston Moore

We provide guarantees for approximate Gaussian Process (GP) regression resulting from two common low-rank kernel approximations: based on random Fourier features, and based on truncating the kernel's Mercer expansion. In particular, we…

机器学习 · 统计学 2022-02-22 Constantinos Daskalakis , Petros Dellaportas , Aristeidis Panos

We provide guarantees for approximate Gaussian Process (GP) regression resulting from two common low-rank kernel approximations: based on random Fourier features, and based on truncating the kernel's Mercer expansion. In particular, we…

机器学习 · 统计学 2021-12-16 Constantinos Daskalakis , Petros Dellaportas , Aristeidis Panos

Existing statistical learning guarantees for general kernel regressors often yield loose bounds when used with finite-rank kernels. Yet, finite-rank kernels naturally appear in several machine learning problems, e.g.\ when fine-tuning a…

机器学习 · 计算机科学 2023-10-04 Tin Sum Cheng , Aurelien Lucchi , Ivan Dokmanić , Anastasis Kratsios , David Belius

This paper concerns the distributed training of nonlinear kernel machines on Map-Reduce. We show that a re-formulation of Nystr\"om approximation based solution which is solved using gradient based techniques is well suited for this,…

机器学习 · 计算机科学 2014-05-20 Dhruv Mahajan , S. Sathiya Keerthi , S. Sundararajan

The ability to train randomly initialised deep neural networks is known to depend strongly on the variance of the weight matrices and biases as well as the choice of nonlinear activation. Here we complement the existing geometric analysis…

信息论 · 计算机科学 2021-02-09 Jared Tanner , Giuseppe Ughi

Recent empirical work has shown that hierarchical convolutional kernels inspired by convolutional neural networks (CNNs) significantly improve the performance of kernel methods in image classification tasks. A widely accepted explanation…

机器学习 · 统计学 2022-06-06 Theodor Misiakiewicz , Song Mei

Low-rank approximation of a matrix by means of random sampling has been consistently efficient in its empirical studies by many scientists who applied it with various sparse and structured multipliers, but adequate formal support for this…

数值分析 · 数学 2016-06-07 Victor Y. Pan , Liang Zhao

We present a new kernel-based algorithm for modeling evenly distributed multidimensional datasets that does not rely on input space sparsification. The presented method reorganizes the typical single-layer kernel-based model into a deep…

机器学习 · 计算机科学 2020-05-01 Hossein Mohamadipanah , Mahdi Heydari , Girish Chowdhary

In this paper, we propose a novel approach for implicit data representation to evaluate similarity of input data using a trained neural network. In contrast to the previous approach, which uses gradients for representation, we utilize only…

机器学习 · 计算机科学 2020-10-12 Alan Savushkin , Nikita Benkovich , Dmitry Golubev

In this paper, we establish universal approximation theorems for neural networks applied to general nonlinear ill-posed operator equations. In addition to the approximation error, the measurement error is also taken into account in our…

数值分析 · 数学 2025-11-21 Lan Wang , Qiao Zhu , Bangti Jin , Ye Zhang

We present a simple linear regression based approach for learning the weights and biases of a neural network, as an alternative to standard gradient based backpropagation. The present work is exploratory in nature, and we restrict the…

机器学习 · 计算机科学 2023-07-17 Harshad Khadilkar

Marginalising over families of Gaussian Process kernels produces flexible model classes with well-calibrated uncertainty estimates. Existing approaches require likelihood evaluations of many kernels, rendering them prohibitively expensive…

机器学习 · 统计学 2023-03-16 Saad Hamid , Sebastian Schulze , Michael A. Osborne , Stephen J. Roberts

We prove some new results concerning the approximation rate of neural networks with general activation functions. Our first result concerns the rate of approximation of a two layer neural network with a polynomially-decaying non-sigmoidal…

经典分析与常微分方程 · 数学 2021-01-05 Jonathan W. Siegel , Jinchao Xu

In recent years, neural networks have revolutionized various domains, yet challenges such as hyperparameter tuning and overfitting remain significant hurdles. Bayesian neural networks offer a framework to address these challenges by…

机器学习 · 计算机科学 2025-12-16 Hayk Amirkhanian , Marco F. Huber

In a recently published paper [1], it is shown that deep neural networks (DNNs) with random Gaussian weights preserve the metric structure of the data, with the property that the distance shrinks more when the angle between the two data…

机器学习 · 统计学 2019-04-02 Talha Cihad Gulcu , Alper Gungor

This note responds to "Promises and Pitfalls of Deep Kernel Learning" (Ober et al., 2021). The marginal likelihood of a Gaussian process can be compartmentalized into a data fit term and a complexity penalty. Ober et al. (2021) shows that…

机器学习 · 统计学 2025-09-26 Andrew Gordon Wilson , Zhiting Hu , Ruslan Salakhutdinov , Eric P. Xing

It has been proposed that random wide neural networks near Gaussian process are quantum field theories around Gaussian fixed points. In this paper, we provide a novel map with which a wide class of quantum mechanical systems can be cast…

高能物理 - 理论 · 物理学 2024-03-19 Koji Hashimoto , Yuji Hirono , Jun Maeda , Jojiro Totsuka-Yoshinaka
‹ 上一页 1 8 9 10 下一页 ›