English
Related papers

Related papers: Nonlinear spiked covariance matrices and signal pr…

200 papers

We study the eigenvalue distributions of the Conjugate Kernel and Neural Tangent Kernel associated to multi-layer feedforward neural networks. In an asymptotic regime where network width is increasing linearly in sample size, under random…

Machine Learning · Statistics 2020-10-13 Zhou Fan , Zhichao Wang

Recent work in random matrix theory (RMT) has developed the notion of deterministic equivalents: typically linear surrogate models that approximate the spectral behavior of large nonlinear random matrices, such as nonlinear feature maps in…

Machine Learning · Statistics 2026-05-29 Collin Cranston , Zhichao Wang , Todd Kemp , Michael W. Mahoney

Random matrix theory has proven to be a valuable tool in analyzing the generalization of linear models. However, the generalization properties of even two-layer neural networks trained by gradient descent remain poorly understood. To…

Statistics Theory · Mathematics 2024-10-21 Jiping Li , Rishi Sonthalia

The spiked covariance model has gained increasing popularity in high-dimensional data analysis. A fundamental problem is determination of the number of spiked eigenvalues, $K$. For estimation of $K$, most attention has focused on the use of…

Methodology · Statistics 2021-01-07 Zheng Tracy Ke , Yucong Ma , Xihong Lin

This paper is concerned with the asymptotic distribution of the largest eigenvalues for some nonlinear random matrix ensemble stemming from the study of neural networks. More precisely we consider $M= \frac{1}{m} YY^\top$ with $Y=f(WX)$…

Probability · Mathematics 2022-01-14 Lucas Benigni , Sandrine Péché

In high-dimensional principal component analysis, important inferential targets include both leading spikes and the associated principal eigenspaces. Such problems arise naturally in high-dimensional factor models, where leading principal…

Statistics Theory · Mathematics 2026-03-26 Yanqing Yin , Wang Zhou

In this paper, we study the asymptotic behavior of the extreme eigenvalues and eigenvectors of the high dimensional spiked sample covariance matrices, in the supercritical case when a reliable detection of spikes is possible. Especially, we…

Statistics Theory · Mathematics 2020-09-04 Zhigang Bao , Xiucai Ding , Jingming Wang , Ke Wang

In this paper, we study the convergent limits and rates of the eigenvalues and eigenvectors for spiked sample covariance matrices whose spectrum can have multiple bulk components. Our model is an extension of Johnstone's spiked covariance…

Probability · Mathematics 2020-01-01 Xiucai Ding

Kernel methods are powerful tools to capture nonlinear patterns behind data. They implicitly learn high (even infinite) dimensional nonlinear features in the Reproducing Kernel Hilbert Space (RKHS) while making the computation tractable by…

Machine Learning · Statistics 2017-11-28 Shuai Zhang , Jianxin Li , Pengtao Xie , Yingchun Zhang , Minglai Shao , Haoyi Zhou , Mengyi Yan

Recent works have demonstrated that the sample complexity of gradient-based learning of single index models, i.e. functions that depend on a 1-dimensional projection of the input data, is governed by their information exponent. However,…

Machine Learning · Statistics 2023-09-08 Alireza Mousavi-Hosseini , Denny Wu , Taiji Suzuki , Murat A. Erdogdu

In this paper, we investigate the asymptotic behaviors of the extreme eigenvectors in a general spiked covariance matrix, where the dimension and sample size increase proportionally. We eliminate the restrictive assumption of the block…

Statistics Theory · Mathematics 2024-05-15 Zhangni Pu , Xiaozhuo Zhang , Jiang Hu , Zhidong Bai

Many real-world datasets contain hidden structure that cannot be detected by simple linear correlations between input features. For example, latent factors may influence the data in a coordinated way, even though their effect is invisible…

The eigenvalue distribution of the Hessian matrix plays a crucial role in understanding the optimization landscape of deep neural networks. Prior work has attributed the well-documented ``bulk-and-spike'' spectral structure, where a few…

Machine Learning · Computer Science 2026-05-26 Shenyang Deng , Boyao Liao , Zhuoli Ouyang , Tianyu Pang , Yaoqing Yang

Are neural networks biased toward simple functions? Does depth always help learn more complex features? Is training the last layer of a network as good as training all layers? How to set the range for learning rate tuning? These questions…

Machine Learning · Computer Science 2020-04-10 Greg Yang , Hadi Salman

Efficient schemes for sampling from the eigenvalues of the Wishart distribution have recently been described for both the uncorrelated central case (where the covariance matrix is $\mathbf{I}$) and the spiked Wishart with a single spike…

Computation · Statistics 2024-10-10 Thomas G. Brooks

We study the asymptotic behavior of the spectrum of a random matrix where a non-linearity is applied entry-wise to a Wigner matrix perturbed by a rank-one spike with independent and identically distributed entries. In this setting, we show…

Probability · Mathematics 2023-10-24 Alice Guionnet , Justin Ko , Florent Krzakala , Pierre Mergny , Lenka Zdeborová

In a spiked population model, the population covariance matrix has all its eigenvalues equal to units except for a few fixed eigenvalues (spikes). Determining the number of spikes is a fundamental problem which appears in many scientific…

Statistics Theory · Mathematics 2011-04-18 Damien Passemier , Jian-Feng Yao

We study the asymptotic distributions of the spiked eigenvalues and the largest nonspiked eigenvalue of the sample covariance matrix under a general covariance matrix model with divergent spiked eigenvalues, while the other eigenvalues are…

Statistics Theory · Mathematics 2017-11-07 Tony Cai , Xiao Han , Guangming Pan

This paper investigates the asymptotics of eigenstructure of sample covariance matrix under the spiked covariance matrix model in ultra-high-dimensional settings, where the dimensionality can grow much faster than the sample size with $ p…

Statistics Theory · Mathematics 2026-04-30 Wonjun Seo

Expressiveness and generalization of deep models was recently addressed via the connection between neural networks (NNs) and kernel learning, where first-order dynamics of NN during a gradient-descent (GD) optimization were related to…

Machine Learning · Computer Science 2020-04-21 Dmitry Kopitkov , Vadim Indelman
‹ Prev 1 2 3 10 Next ›