My research efforts are primarily focused on three main thrusts in information sciences: Big data science, sparsity-based and compressive signal processing, and controlled sensing. I seek to understand the fundamental limits for signal reconstruction, data processing and acquisition, as well as design provable scalable and robust learning algorithms and efficient control policies towards achieving the overarching goals of various inference tasks at hand. I study these questions in the context of numerous concrete applications ranging from machine learning and video analytics, to optical imaging, to brain and array signal processing.
NSF CAREER: Inference-Driven Data Processing and Acquisition: Scalability, Robustness and Control, Awarded Feb 2016.
DARPA UNCOVER: Unconstrained Natural light Coherency Vector-field-imaging by Exploiting Randomness (CoPI), DARPA, Awarded Feb 2016.
NSF CIF: Advanced Ion Channel Models for Neurological Signal Processing -- Theory and Application to Brain-Computer Interfacing (PI), NSF, Awarded August 2015.
ONR Exploiting Multidimensional Classical Optical Entanglement for Enhanced Spatial Scene Recognition (CoPI), Office of Naval research (ONR), Awarded June 2014.
NSF CIF: A Unifying Approach for Identification of Sparse Interactions in Large Datasets (PI), NSF CCF/CIF, Awarded August 2013.
NSF I/UCRC Multi-functional Integrated System Technology (MIST) (CoPI), Sep 2014.
Fundamental Limits of Sparse Signal and Information Processing, In-House Award (UCF), Feb. 2013.