Non-PSD Matrix Sketching with Applications to Regression and Optimization

by   Zhili Feng, et al.

A variety of dimensionality reduction techniques have been applied for computations involving large matrices. The underlying matrix is randomly compressed into a smaller one, while approximately retaining many of its original properties. As a result, much of the expensive computation can be performed on the small matrix. The sketching of positive semidefinite (PSD) matrices is well understood, but there are many applications where the related matrices are not PSD, including Hessian matrices in non-convex optimization and covariance matrices in regression applications involving complex numbers. In this paper, we present novel dimensionality reduction methods for non-PSD matrices, as well as their “square-roots", which involve matrices with complex entries. We show how these techniques can be used for multiple downstream tasks. In particular, we show how to use the proposed matrix sketching techniques for both convex and non-convex optimization, ℓ_p-regression for every 1 ≤ p ≤∞, and vector-matrix-vector queries.



There are no comments yet.


page 1

page 2

page 3

page 4


Isometric sketching of any set via the Restricted Isometry Property

In this paper we show that for the purposes of dimensionality reduction ...

Matrix Completion has No Spurious Local Minimum

Matrix completion is a basic machine learning problem that has wide appl...

Learning-Augmented Sketches for Hessians

Sketching is a dimensionality reduction technique where one compresses a...

MKL-RT: Multiple Kernel Learning for Ratio-trace Problems via Convex Optimization

In the recent past, automatic selection or combination of kernels (or fe...

Safe squeezing for antisparse coding

Spreading the information over all coefficients of a representation is a...

On Convolutional Approximations to Linear Dimensionality Reduction Operators for Large Scale Data Processing

In this paper, we examine the problem of approximating a general linear ...

Sublinear Time Approximation of Text Similarity Matrices

We study algorithms for approximating pairwise similarity matrices that ...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.