Rigorous Restricted Isometry Property of Low-Dimensional Subspaces

01/30/2018
by   Gen Li, et al.
0

Dimensionality reduction is in demand to reduce the complexity of solving large-scale problems with data lying in latent low-dimensional structures in machine learning and computer version. Motivated by such need, in this work we study the Restricted Isometry Property (RIP) of Gaussian random projections for low-dimensional subspaces in R^N, and rigorously prove that the projection Frobenius norm distance between any two subspaces spanned by the projected data in R^n (n<N) remain almost the same as the distance between the original subspaces with probability no less than 1 - e^-O(n). Previously the well-known Johnson-Lindenstrauss (JL) Lemma and RIP for sparse vectors have been the foundation of sparse signal processing including Compressed Sensing. As an analogy to JL Lemma and RIP for sparse vectors, this work allows the use of random projections to reduce the ambient dimension with the theoretical guarantee that the distance between subspaces after compression is well preserved.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/22/2018

Enhanced Expressive Power and Fast Training of Neural Networks by Random Projections

Random projections are able to perform dimension reduction efficiently f...
research
12/01/2021

Invariance principle of random projection for the norm

Johnson-Lindenstrauss guarantees certain topological structure is preser...
research
08/31/2021

ℓ_p-Spread Properties of Sparse Matrices

Random subspaces X of ℝ^n of dimension proportional to n are, with high ...
research
03/06/2017

Generalizing CoSaMP to Signals from a Union of Low Dimensional Linear Subspaces

The idea that signals reside in a union of low dimensional subspaces sub...
research
07/14/2016

Random projections of random manifolds

Interesting data often concentrate on low dimensional smooth manifolds i...
research
08/02/2012

Efficient Point-to-Subspace Query in ℓ^1 with Application to Robust Object Instance Recognition

Motivated by vision tasks such as robust face and object recognition, we...
research
06/14/2022

Overparametrized linear dimensionality reductions: From projection pursuit to two-layer neural networks

Given a cloud of n data points in ℝ^d, consider all projections onto m-d...

Please sign up or login with your details

Forgot password? Click here to reset