Random Projections for Manifold Learning: Proofs and Analysis

TitleRandom Projections for Manifold Learning: Proofs and Analysis
Publication TypeReport
AuthorsC. Hegde, M. B. Wakin, and R. G. Baraniuk
Abstract

We derive theoretical bounds on the performance of manifold learning algorithms, given access to a small number of random projections of the input dataset. We prove that with the number of projections only logarithmic in the size of the original space, we may reliably learn the structure of the nonlinear manifold, as compared to performing conventional manifold learning on the full dataset.

Year of Publication2007
MonthOct.
Technical Report NumberTREE0710
InstitutionRice University, Department of Electrical and Computer Engineering
Acknowledgements

This work was supported by research grants DARPA/ONR N66001-06-1-2011 and N00014-06-1-0610, NSF CCF-0431150, ONR N00014-07-1-0936, AFOSR FA9550-07-1-0301, ARO W911NF-07-1-0502, ARO MURI W311NF-07-1-0185, and the Texas Instruments Leadership University Program.

Publication File: 

Rice University, MS-380 - 6100 Main St - Houston, TX 77005 - USA - webmaster-dsp@ece.rice.edu