Figure - PMC

Skip to main content

An official website of the United States government

Here's how you know

Here's how you know

Official websites use .gov
A .gov website belongs to an official government organization in the United States.

Secure .gov websites use HTTPS
A lock ( ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

View full-text article in PMC

. 2016 Feb 26;6:21963. doi: 10.1038/srep21963

Search in PMC
Search in PubMed
View in NLM Catalog
Add to search

Copyright © 2016, Macmillan Publishers Limited

This work is licensed under a Creative Commons Attribution 4.0 International License. The images or other third party material in this article are included in the article’s Creative Commons license, unless indicated otherwise in the credit line; if the material is not included under the Creative Commons license, users will need to obtain permission from the license holder to reproduce the material. To view a copy of this license, visit http://creativecommons.org/licenses/by/4.0/

PMC Copyright notice

Histograms summarizing the relative performance of ND and -min approaches for the benchmark numerical case in terms of (a) inference error that quantifies the accuracy and (b) Hoyer measure that quantifies the sparsity of the solution. The solution from the -min approach is more precise and sparser than ND: compared to NDs, the mean and the variance of the inference error are reduced by 45% and 99%, respectively, when using -min with ; 33.5% and 87.5%, respectively when using -min with ; the mean of Hoyer measure is increased by 16.38% and variance reduced by 69% when using the -min with , and is increased by 15.90% in mean, reduced by 75.69% in variance when using .

Inline graphic — Histograms summarizing the relative performance of ND and -min approaches for the benchmark numerical case in terms of (a) inference error that quantifies the accuracy and (b) Hoyer measure that quantifies the sparsity of the solution. The solution from the -min approach is more precise and sparser than ND: compared to NDs, the mean and the variance of the inference error are reduced by 45% and 99%, respectively, when using -min with ; 33.5% and 87.5%, respectively when using -min with ; the mean of Hoyer measure is increased by 16.38% and variance reduced by 69% when using the -min with , and is increased by 15.90% in mean, reduced by 75.69% in variance when using .