Non-Gaussian Observations in Nonlinear Compressed Sensing via Stein Discrepancies
Statistics Theory
2017-10-03 v2 Probability
Statistics Theory
Abstract
Performance guarantees for compression in nonlinear models under non-Gaussian observations can be achieved through the use of distributional characteristics that are sensitive to the distance to normality, and which in particular return the value of zero under Gaussian or linear sensing. The use of these characteristics, or discrepancies, improves some previous results in this area by relaxing conditions and tightening performance bounds. In addition, these characteristics are tractable to compute when Gaussian sensing is corrupted by either additive errors or mixing.
Cite
@article{arxiv.1609.08512,
title = {Non-Gaussian Observations in Nonlinear Compressed Sensing via Stein Discrepancies},
author = {Larry Goldstein and Xiaohan Wei},
journal= {arXiv preprint arXiv:1609.08512},
year = {2017}
}
Comments
31 pages