Relating Leverage Scores and Density using Regularized Christoffel Functions

by   Edouard Pauwels, et al.

Statistical leverage scores emerged as a fundamental tool for matrix sketching and column sampling with applications to low rank approximation, regression, random feature learning and quadrature. Yet, the very nature of this quantity is barely understood. Borrowing ideas from the orthogonal polynomial literature, we introduce the regularized Christoffel function associated to a positive definite kernel. This uncovers a variational formulation for leverage scores for kernel methods and allows to elucidate their relationships with the chosen kernel as well as population density. Our main result quantitatively describes a decreasing relation between leverage score and population density for a broad class of kernels on Euclidean spaces. Numerical simulations support our findings.


page 1

page 2

page 3

page 4


Generalized Leverage Score Sampling for Neural Networks

Leverage score sampling is a powerful technique that originates from the...

On Fast Leverage Score Sampling and Optimal Learning

Leverage score sampling provides an appealing way to perform approximate...

On Column Selection in Approximate Kernel Canonical Correlation Analysis

We study the problem of column selection in large-scale kernel canonical...

An Explicit Sampling Dependent Spectral Error Bound for Column Subset Selection

In this paper, we consider the problem of column subset selection. We pr...

Large Scale Learning with Kreĭn Kernels

We extend the Nyström method for low-rank approximation of positive defi...

On Sampling Random Features From Empirical Leverage Scores: Implementation and Theoretical Guarantees

Random features provide a practical framework for large-scale kernel app...

Kernel interpolation with continuous volume sampling

A fundamental task in kernel methods is to pick nodes and weights, so as...

Please sign up or login with your details

Forgot password? Click here to reset