paper-with-me

홈 › Papers

Concentration of Random Feature Matrices in High-Dimensions

2022-04-14 · Zhijun Chen, Hayden Schaeffer, Rachel Ward

The spectra of random feature matrices provide essential information on the conditioning of the linear system used in random feature regression problems and are thus connected to the consistency and generalization of random feature models. Random feature matrices are asymmetric rectangular nonlinear matrices depending on two input variables, the data and the weights, which can make their characterization challenging. We consider two settings for the two input variables, either both are random variables or one is a random variable and the other is well-separated, i.e. there is a minimum distance between points. With conditions on the dimension, the complexity ratio, and the sampling variance, we show that the singular values of these matrices concentrate near their full expectation and near one with high-probability. In particular, since the dimension depends only on the logarithm of the number of random weights or the number of data points, our complexity bounds can be achieved even in moderate dimensions for many practical setting. The theoretical results are verified with numerical experiments.

📄 PDF Abstract BibTeX arXiv:2204.06935

Code (0)

등록된 구현이 없습니다.

Tasks

Vocal Bursts Intensity Prediction

Similar Papers 제목 키워드 기반

Concentration of measure for non-linear random matrices with applications to neural networks and non-commutative polynomials

2025-07-10 · Radosław Adamczak arxiv

We prove concentration inequalities for several models of non-linear random matrices. As corollaries we obtain estimates for linear spectral statistics of the conjugate kernel of neural networks and non-commutative polyn…

Random Embeddings with Optimal Accuracy

2020-12-31 · Maciej Skorski

This work constructs Jonson-Lindenstrauss embeddings with best accuracy, as measured by variance, mean-squared error and exponential concentration of the length distortion. Lower bounds for any data and embedding dimensi…

Concentration of polynomial random matrices via Efron-Stein inequalities

2022-09-06 · Goutham Rajendran, Madhur Tulsiani

Analyzing concentration of large random matrices is a common task in a wide variety of fields. Given independent random variables, many tools are available to analyze random matrices whose entries are linear in the varia…

Tensor Networks

Spectral Properties of Radial Kernels and Clustering in High Dimensions

2019-06-25 · David Cohen-Steiner, Alba Chiara de Vitis

In this paper, we study the spectrum and the eigenvectors of radial kernels for mixtures of distributions in $\mathbb{R}^n$. Our approach focuses on high dimensions and relies solely on the concentration properties of th…

ClusteringVocal Bursts Intensity Prediction

Isometric sketching of any set via the Restricted Isometry Property

2015-06-11 · Samet Oymak, Benjamin Recht, Mahdi Soltanolkotabi

In this paper we show that for the purposes of dimensionality reduction certain class of structured random matrices behave similarly to random Gaussian matrices. This class includes several matrices for which matrix-vect…

Dimensionality Reduction