Siegel Hall Auditorium
3310 S. Dearborn
Chicago, IL 60616
The Electrical and Computer Engineering department will be hosting a seminar featuring Dr. Mojtaba Soltanalian, Deshpande, Professor for the Electrical and Computer Engineering Department, UIC. Dr. Soltanalian will speak on " Guaranteed Signal Processing and Learning with Partial Information."
Dr. Soltanalian will begin by discussing various signal processing and learning problems dealing with partial information, ranging from classical questions in sensing and communications to more modern data processing challenges in disparate data fusion, matrix completion and data clustering. Particularly, he will discuss different approaches to exploit one-bit sampled data and comparison information for inference and learning. There are many immediate natural applications to such data processing ideas. For example, in streaming services, companies can look at novel movie rating matrix recovery algorithms that operate only by exploiting movie comparison information. Since users (particularly those less familiar with the rating system) are more comfortable with comparing movies than giving exact ratings, such an approach is expected to make the user interface of the rating system more friendly, and possibly make the ratings more precise.
Also to be discussed, the issue of reliability and trust in learning and inference—a problem with even more significance when the information is partially available. Considering the strong connection of such learning and inference guarantees with those in the mathematical optimization literature, Professor Soltanalian will introduce the idea of MERIT, a monotonically error-bound improving technique for optimization. MERIT is a novel optimization framework that lays the ground for obtaining computational data-dependent sub-optimality guarantees for the obtained approximate solutions. The new guarantees typically outperform the a priori known guarantees of some widely used data processing methods such as the semidefinite relaxation.
Before joining UIC, Dr. Soltanalian held research positions at the Interdisciplinary Centre for Security, Reliability and Trust (SnT, University of Luxembourg), and California Institute of Technology (Caltech). His research interests lie in the interplay of signal processing, learning and optimization theory, and specifically different ways optimization theory can facilitate a better processing and design of signals for collecting information, communication, as well as to form a more profound understanding of data— whether it is in everyday applications or in large-scale, complex scenarios. He serves as a member of the editorial board of Signal Processing, and as the Vice Chair of the IEEE Signal Processing Society Chapter in Chicago. Dr. Soltanalian has been a recipient of the 2017 IEEE Signal Processing Society (SPS) Young Author Best Paper Award, as well as the 2018 European Signal Processing Association (EURASIP) Best PhD Award.