Welcome to the new version of CaltechAUTHORS. Login is currently restricted to library staff. If you notice any issues, please email coda@library.caltech.edu
Published June 21, 2021 | Submitted
Report Open

Tensor Random Projection for Low Memory Dimension Reduction

Abstract

Random projections reduce the dimension of a set of vectors while preserving structural information, such as distances between vectors in the set. This paper proposes a novel use of row-product random matrices in random projection, where we call it Tensor Random Projection (TRP). It requires substantially less memory than existing dimension reduction maps. The TRP map is formed as the Khatri-Rao product of several smaller random projections, and is compatible with any base random projection including sparse maps, which enable dimension reduction with very low query cost and no floating point operations. We also develop a reduced variance extension. We provide a theoretical analysis of the bias and variance of the TRP, and a non-asymptotic error analysis for a TRP composed of two smaller maps. Experiments on both synthetic and MNIST data show that our method performs as well as conventional methods with substantially less storage.

Attached Files

Submitted - 2105.00105.pdf

Files

2105.00105.pdf
Files (609.4 kB)
Name Size Download all
md5:31679585d2d806f7ab1106ff9058a74b
609.4 kB Preview Download

Additional details

Created:
August 20, 2023
Modified:
October 23, 2023