Fast Fixed Dimension L2-Subspace Embeddings of Arbitrary Accuracy, With Application to L1 and L2 Tasks

09/27/2019
by   Malik Magdon-Ismail, et al.
0

We give a fast oblivious L2-embedding of A∈R^n x d to B∈R^r x d satisfying (1-ε)A x_2^2 <B x_2^2 <= (1+ε) Ax_2^2. Our embedding dimension r equals d, a constant independent of the distortion ε. We use as a black-box any L2-embedding Π^T A and inherit its runtime and accuracy, effectively decoupling the dimension r from runtime and accuracy, allowing downstream machine learning applications to benefit from both a low dimension and high accuracy (in prior embeddings higher accuracy means higher dimension). We give applications of our L2-embedding to regression, PCA and statistical leverage scores. We also give applications to L1: 1.) An oblivious L1-embedding with dimension d+O(d^1+η d) and distortion O((d d)/ d), with application to constructing well-conditioned bases; 2.) Fast approximation of L1-Lewis weights using our L2 embedding to quickly approximate L2-leverage scores.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
01/13/2018

Tight Bounds for ℓ_p Oblivious Subspace Embeddings

An ℓ_p oblivious subspace embedding is a distribution over r × n matrice...
research
07/16/2019

Lossless Prioritized Embeddings

Given metric spaces (X,d) and (Y,ρ) and an ordering x_1,x_2,...,x_n of (...
research
09/25/2019

Mixed Dimension Embeddings with Application to Memory-Efficient Recommendation Systems

In many real-world applications, e.g. recommendation systems, certain it...
research
12/31/2019

Computing L1 Straight-Line Fits to Data (Part 1)

The initial remarks in this technical report are primarily for those not...
research
07/19/2012

The Fast Cauchy Transform and Faster Robust Linear Regression

We provide fast algorithms for overconstrained ℓ_p regression and relate...
research
10/17/2021

Terminal Embeddings in Sublinear Time

Recently (Elkin, Filtser, Neiman 2017) introduced the concept of a termi...
research
12/29/2014

Improving approximate RPCA with a k-sparsity prior

A process centric view of robust PCA (RPCA) allows its fast approximate ...

Please sign up or login with your details

Forgot password? Click here to reset