Provable Deterministic Leverage Score Sampling

04/06/2014
by   Dimitris Papailiopoulos, et al.
0

We explain theoretically a curious empirical phenomenon: "Approximating a matrix by deterministically selecting a subset of its columns with the corresponding largest leverage scores results in a good low-rank matrix surrogate". To obtain provable guarantees, previous work requires randomized sampling of the columns with probabilities proportional to their leverage scores. In this work, we provide a novel theoretical analysis of deterministic leverage score sampling. We show that such deterministic sampling can be provably as accurate as its randomized counterparts, if the leverage scores follow a moderately steep power-law decay. We support this power-law assumption by providing empirical evidence that such decay laws are abundant in real-world data sets. We then demonstrate empirically the performance of deterministic leverage score sampling, which many times matches or outperforms the state-of-the-art techniques.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
03/15/2018

Ridge Regression and Provable Deterministic Ridge Leverage Score Sampling

Ridge leverage scores provide a balance between low-rank approximation a...
research
05/04/2015

An Explicit Sampling Dependent Spectral Error Bound for Column Subset Selection

In this paper, we consider the problem of column subset selection. We pr...
research
06/12/2013

Completing Any Low-rank Matrix, Provably

Matrix completion, i.e., the exact and provable recovery of a low-rank m...
research
05/17/2015

Provably Correct Algorithms for Matrix Column Subset Selection with Selectively Sampled Data

We consider the problem of matrix column subset selection, which selects...
research
03/03/2013

Sparse PCA through Low-rank Approximations

We introduce a novel algorithm that computes the k-sparse principal comp...
research
11/17/2021

A quantum-inspired algorithm for approximating statistical leverage scores

Suppose a matrix A ∈ℝ^m × n of rank k with singular value decomposition ...
research
05/29/2019

Nyström landmark sampling and regularized Christoffel functions

Selecting diverse and important items from a large set is a problem of i...

Please sign up or login with your details

Forgot password? Click here to reset