GMRA Regression

Project Summary

We present a framework for high-dimensional regression using the GMRA data structure. In analogy to a classical wavelet decomposition of function spaces, a GMRA is a tree-based decomposition of a data set into local linear projections.

Themes and Categories
Year
Contact
David Lawlor
Mathematics
djl@math.duke.edu

Moreover, for new points, GMRA admits a fast algorithm for computing the projection coefficients on the already-learned dictionary. Within each node of the tree one can also assign regression coefficients in any manner; here we study the simple case of weighted linear regression. We explore the performance of the method using synthetic data as well as galactic spectra from the Sloan Digital Sky Survey, and compare against other methods for regression in high dimensions.

Related People

Related Projects

Sean Fiscus (Math/Econ/EnvEng), Alyssa Shi (Stats), Yamil Lopez-Ruiz (BME/CS), Emmanuel Mokel (Stats/Math) spent ten weeks working with data from CovIdentify, a study that focuses on using wearables to predict and diagnose COVID-19 and the Flu. The team improved the memory efficiency of analytic pipelines, and added capacity to ingest different types of data. This project built upon the work accomplished by the Duke Bass Connections team and the Duke MIDS capstone project.

 

View the team's project poster here

Watch the team's final presentation on Zoom:

 

Project Lead: Jessilyn Dunn

Stats majors Alexandra Lawrence and Morgan Pruchniewski spent ten weeks exploring a dataset comprising 619 variables, including chemical and biological measurements, sourced from the Pivers Island Coastal Observatory (PICO). Using modern time-series analysis techniques, the team delivered key insights to PICO scientific staff, as well as advice for future data collection protocols.

 

View the team's project poster here

Watch the team's final presentation on Zoom:

 

Project Lead: Zackary Johnson

Marine mammals exhibit extreme physiological and behavioral adaptions that allow them to dive hundreds to thousands of meters underwater despite their need to breathe air at the surface. Through the development of new remote monitoring technologies, we are just beginning to understand the mechanisms by which they are able to execute these extreme behaviors. Long- term animal-borne tags can now record location, dive depth, and dive duration and then transmit these data to satellite receivers, enabling remote access to behavior occurring both many kilometers out to sea and several kilometers below the ocean surface.