Learning-Based Dimensionality Reduction
[PhD Students: Rabeeh Karimi and Arda Uran– Jointly funded by Hasler Stiftung, Postdoc: Junhong Lin]
This project seeks to enhance the applicability of adaptive sampling, overcoming the limitations of conventional techniques and simplistic models by developing techniques that learn the required information directly from data.
Aside from the broader impact in settings where data compression is relevant, we pursue a number of particularly important specific applications, including medical imaging and array signal processing, which relate to the core of cyber-human systems. This project is highly-interdisciplinary, and aims to strengthen connections between the areas of machine learning, signal processing, and optimization, and will result in new sampling theory and methods.