January 9, 2026 at 12:00 (Multimedia Amphitheater, Central Library of NTUA)

Title: Multiview learning-based signal processing with applications in wireless communications and brain fMRI

Abstract: How can we communicate reliably in the presence of strong interference from a nearby station or WiFi router? How can we tease out visual stimulus-induced responses from background brain activity in multi-subject fMRI data? Both tasks can be handled using multiview signal processing that builds upon statistical learning tools under the umbrella of canonical correlation analysis (CCA). In this talk, we will revisit the foundations of generalized linear and nonlinear ("deep") CCA from algebraic, geometric and probabilistic points of view and highlight recent theoretical insights and how they can be used to drive applications. We will start from the first application: sliding information under strong interference. We will show how CCA can be used to recover an underlay communication signal by intersecting two or more multichannel mixtures that contain the sought signal in their span. This is a rare example where math can be more-or-less directly used to solve a practical problem -- and we have demonstrated this in over-the-air experiments with software radios. Then, we will delve into CCA theory and methods before returning to discuss brain fMRI and other applications.

Bio: Nicholas D. Sidiropoulos (Fellow, IEEE) received the Diploma in electrical engineering from Aristotle University of Thessaloniki, Greece, and the M.S. and Ph.D. degrees in electrical engineering from the University of Maryland at College Park, MD, USA, in 1988, 1990, and 1992, respectively. He is the Louis T. Rader Professor of ECE at the University of Virginia. He has previously served on the faculty of the University of Minnesota and the Technical University of Crete, Greece. His research interests are in signal processing, communications, optimization, tensor decomposition, and machine learning. He received the NSF/CAREER award in 1998, the IEEE Signal Processing Society (SPS) Best Paper Award in 2001, 2007, 2011, and 2022, and the IEEE SPS Donald G. Fink Overview Paper Award in 2022. He served as IEEE SPS Distinguished Lecturer (2008–2009), Vice President—Membership of the IEEE SPS (2017–2019), and as Chair of the IEEE SPS Fellow Evaluation Committee (2020–2021). He received the 2010 IEEE SPS Meritorious Service Award, the 2013 Distinguished Alumni Award of the ECE Department, University of Maryland, the 2022 EURASIP Technical Achievement Award, and the 2022 IEEE SPS Claude Shannon–Harry Nyquist Technical Achievement Award. He is a fellow of EURASIP (2014).