Spatial Random Sampling: A Structure-Preserving Data Sketching Tool
Keywords
Big data; clustering; column sampling; data sketching; random embedding; unit sphere
Abstract
Random column sampling is not guaranteed to yield data sketches that preserve the underlying structures of the data and may not sample sufficiently from less-populated data clusters. Also, adaptive sampling can often provide accurate low rank approximations, yet may fall short of producing descriptive data sketches, especially when the cluster centers are linearly dependent. Motivated by that, this letter introduces a novel randomized column sampling tool dubbed spatial random sampling (SRS), in which data points are sampled based on their proximity to randomly sampled points on the unit sphere. The most compelling feature of SRS is that the corresponding probability of sampling from a given data cluster is proportional to the surface area the cluster occupies on the unit sphere, independently of the size of the cluster population. Although it is fully randomized, SRS is shown to provide descriptive and balanced data representations. The proposed idea addresses a pressing need in data science and holds potential to inspire many novel approaches for analysis of big data.
Publication Date
9-1-2017
Publication Title
IEEE Signal Processing Letters
Volume
24
Issue
9
Number of Pages
1398-1402
Document Type
Article
Personal Identifier
scopus
DOI Link
https://doi.org/10.1109/LSP.2017.2723472
Copyright Status
Unknown
Socpus ID
85023201871 (Scopus)
Source API URL
https://api.elsevier.com/content/abstract/scopus_id/85023201871
STARS Citation
Rahmani, Mostafa and Atia, George K., "Spatial Random Sampling: A Structure-Preserving Data Sketching Tool" (2017). Scopus Export 2015-2019. 5237.
https://stars.library.ucf.edu/scopus2015/5237