The paper demonstrates the feasibility of building scalable linear algebra on top of a parallel/distributed relational database system to facilitate large-scale data analytics.
In "Scalable Linear Algebra on a Relational Database System
", the authors approach the problem of large-scale linear algebra computation from a new direction. Instead of the popular practice of building new systems from the ground up to support such calculations, they made a few changes to existing relational technology to achieve similar results, and realized in-databasedata analytics.
Shangyu Luo, Zekai "Jacob" Gao, Michael Gubanov, and Luis Perez co-wrote the paper with Jermaine. Luo and Gao are current CS Ph.D. students at Rice. Perez was advised by Jermaine and earned his CS Ph.D. in 2014. Gubanov, now the Cloud Technology Endowed Assistant Professor at the University of Texas at San Antonio, worked on the project with Jermaine while a postdoctoral researcher at Rice.
Photo of Gubanov (left), Jermaine, and Luo by Chaitan Baru, Senior Advisor for Data Science at the National Science Foundation.