DeepAI AI Chat
Log In Sign Up

On Fast Leverage Score Sampling and Optimal Learning

by   Alessandro Rudi, et al.
Istituto Italiano di Tecnologia
Università di Genova

Leverage score sampling provides an appealing way to perform approximate computations for large matrices. Indeed, it allows to derive faithful approximations with a complexity adapted to the problem at hand. Yet, performing leverage scores sampling is a challenge in its own right requiring further approximations. In this paper, we study the problem of leverage score sampling for positive definite matrices defined by a kernel. Our contribution is twofold. First we provide a novel algorithm for leverage score sampling and second, we exploit the proposed method in statistical learning by deriving a novel solver for kernel ridge regression. Our main technical contribution is showing that the proposed algorithms are currently the most efficient and accurate for these problems.


page 1

page 2

page 3

page 4


Recursive Sampling for the Nyström Method

We give the first algorithm for kernel Nyström approximation that runs i...

Generalized Leverage Score Sampling for Neural Networks

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

Relating Leverage Scores and Density using Regularized Christoffel Functions

Statistical leverage scores emerged as a fundamental tool for matrix ske...

Fast Algorithms for Monotone Lower Subsets of Kronecker Least Squares Problems

Approximate solutions to large least squares problems can be computed ef...

Sketching Matrix Least Squares via Leverage Scores Estimates

We consider the matrix least squares problem of the form 𝐀𝐗-𝐁_F^2 where ...

On Column Selection in Approximate Kernel Canonical Correlation Analysis

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

Max-plus statistical leverage scores

The statistical leverage scores of a complex matrix A∈C^n× d record the ...

Code Repositories


Fast algorithm for leverage score sampling, low rank (kernel) matrix factorization and PCA

view repo