Data Discovery Using Lossless Compression-Based Sparse Representation
Signal Processing
2021-03-18 v2 Information Theory
math.IT
Abstract
Sparse representation has been widely used in data compression, signal and image denoising, dimensionality reduction and computer vision. While overcomplete dictionaries are required for sparse representation of multidimensional data, orthogonal bases represent one-dimensional data well. In this paper, we propose a data-driven sparse representation using orthonormal bases under the lossless compression constraint. We show that imposing such constraint under the Minimum Description Length (MDL) principle leads to a unique and optimal sparse representation for one-dimensional data, which results in discriminative features useful for data discovery.
Keywords
Cite
@article{arxiv.2103.08765,
title = {Data Discovery Using Lossless Compression-Based Sparse Representation},
author = {Elyas Sabeti and Peter X. K. Song and Alfred O. Hero},
journal= {arXiv preprint arXiv:2103.08765},
year = {2021}
}