Lecture

Sparsity-aware adaptive parameter estimation: a Bayesian perspective
23.01.2015
Speaker: Dr. Athanasios Rontogiannis, Senior Researcher
Date: 23 January 2015 Time: 12:00-13:00
Location: "Stelios Orphanoudakis" Seminar Room, FORTH. Heraklion, Crete
Host: Prof. Panagiotis Tsakalides

Abstract:

Adaptive parameter estimation (PE) of linear time-varying systems is a research field that has attracted significant attention in the statistical signal processing literature and has had a great impact in a plethora of applications. Recently, the interest in the area has been revived, thanks to the advancements in the compressive sensing (CS) field, which provide the means to exploit parameter sparsity in a time-varying environment.  By leveraging parameter sparsity, significant improvements in convergence rate and estimation performance of adaptive techniques can be achieved. Unlike most state-of-the-art sparsity-aware adaptive PE techniques, which are deterministic, in this presentation, we will provide an alternative approach stemming from a Bayesian perspective. In this context, both conventional and structured (group-) sparsity schemes will be explored.  In all these schemes, appropriate hierarchical Bayesian models are first defined where sparsity is imposed by assigning heavy-tailed sparsity-promoting priors to the parameters of interest. Then, a variational Bayes inference method is applied to obtain estimates of all parameters involved in the models. The resulting fully automated Bayesian schemes will be first presented in a batch iterative form. Then, it will be shown that by properly exploiting the structure of the batch estimation task, new sparse online Bayesian algorithms can be derived. The most important feature of the proposed algorithms is that they completely eliminate the need for computationally costly parameter fine-tuning, a necessary ingredient of sparse adaptive deterministic algorithms. We will present extensive simulation results on adaptive channel estimation, which demonstrate the effectiveness of the new sparse adaptive variational Bayes algorithms against state-of-the-art deterministic techniques.

Bio:

Athanasios Rontogiannis received the diploma degree in Electrical Engineering from the National Technical University of Athens (NTUA) in 1991, the M.A.Sc.   from the University of Victoria, Canada, in 1993 and the PhD in Signal Processing and Communications from the University of Athens in 1997. From 1998 to 1999, he was a Postdoctoral Scholar at the University of Athens and from 1999 to 2003 he was with the University of Ioannina as a Lecturer in Informatics. In 2003 joined the National Observatory of Athens (NOA), where since 2011 he is a Senior Researcher at the Institute for Astronomy, Astrophysics, Space Applications and Remote Sensing (IAASARS). His research interests are in the general areas of statistical signal processing and wireless communications with emphasis on adaptive estimation, hyperspectral image processing, Bayesian compressive sensing, channel estimation/equalization, multicarrier and cooperative communications. He has co-authored 77 publications on these topics including 2 book chapters, 25 peer-reviewed journal papers and 50 refereed international conference publications. He has participated as PI, co-PI or research coordinator in 5 European Commission and 8 national projects.  He has been in the Technical Program Committee of 15 international conferences, in one of them (DSP-2009) as the Technical Program co-Chair. He is also the co-recipient of one of the two best paper awards in the IEEE ISSPIT 2013 conference. Currently, he serves at the Editorial Boards of the EURASIP Journal on Advances in Signal Processing, Springer (since 2008) and Signal Processing, Elsevier (since 2011). He is member of the IEEE Signal Processing and Communication Societies and the Technical Chamber of Greece.

Conditions of Use | Privacy Policy