dcsimg
Webinar on Optimization for Data-Driven Learning and Control

Webinar on Optimization for Data-Driven Learning and Control

Webinar on Optimization for Data-Driven Learning and Control

12 March 2021, 10 - 11 PM ET

View Event Recording | View Special Issue

Description

Optimization, once considered a niche topic, has transitioned in the last decade into one of the most important workhorses of modern machine learning, artificial intelligence, and control problems. Common to many of these data-rich problems are one or more of the following characteristics that make the use of numerical optimization methods so challenging: massively large datasets, geographically distributed datasets, streaming data, communication and/or computation constraints, privacy issues, and non-convex objective functions. This webinar will provide an overview of the main issues, ideas, and solutions along with key challenges and opportunities, which were presented in the November 2020 special issue on "Optimization for Data-Driven Learning and Control." This issue brought together subject experts from both industry and academia to highlight the interplay between optimization methods and these characteristics of machine learning, artificial intelligence, and control from a number of perspectives that span multiple disciplines. The guest editors and selected contributors will present an overview and introduction to the issue and related topics. Presentations will be followed by Q&A with the panelists.

About the Panelists

Usman A. Khan (Senior Member, IEEE) received the B.S. degree from the University of Engineering and Technology, Lahore, Pakistan, in 2002, the M.S. degree from the University of Wisconsin–Madison, Madison, WI, USA, in 2004, and the Ph.D. degree from Carnegie Mellon University, Pittsburgh, PA, USA, in 2009, all in electrical and computer engineering. He held a postdoctoral position at the GRASP Laboratory, University of Pennsylvania, Philadelphia, PA, USA. In 2011, he joined Tufts University as an Assistant Professor. In Spring 2015, he was a Visiting Professor with KTH, Stockholm, Sweden. He is currently an Associate Professor of electrical and computer engineering (ECE) with Tufts University, Medford, MA, USA, where he is also an Adjunct Professor of computer science. His research interests include signal processing, machine learning, control, and optimization. He has published extensively in these topics with more than 100 papers in journals and conference proceedings and holds multiple patents. Recognition of his work includes the prestigious National Science Foundation (NSF) Career Award, several NSF REU awards, an IEEE journal cover, three best student paper awards in IEEE conferences, and several news articles, including two in IEEE Spectrum. Dr. Khan was an Associate Member of the Sensor Array and Multichannel Technical Committee, IEEE Signal Processing Society, from 2010 to 2019, where he has been an elected full member since 2019. He was an elected full member of the IEEE Big Data Special Interest Group from 2017 to 2019 and has served on the IEEE Young Professionals Committee and the IEEE Technical Activities Board. He is also the Technical Area Chair of the Networks track at the IEEE 2020 Asilomar Conference on Signals Systems and Computers. He has served on the technical program committee of several IEEE conferences and has organized/chaired several IEEE workshops and sessions. He served as an Editor for IEEE Transactions on Smart Grid from 2014 to 2017. He is also serving as an Associate Editor for IEEE Control System Letters, IEEE Transactions on Signal and Information Processing over Networks, and IEEE Open Journal of Signal Processing. He also served as a Guest Associate Editor for the Control System Letters—Special Issue on Learning and Control both to appear in 2020.

Waheed U. Bajwa (Senior Member, IEEE) received the B.E. degree (Honors) in electrical engineering from the National University of Sciences and Technology, Islamabad, Pakistan, in 2001, and the M.S. and Ph.D. degrees in electrical engineering from the University of Wisconsin–Madison, Madison, WI, USA, in 2005 and 2009, respectively. He was a Postdoctoral Research Associate of the Program in Applied and Computational Mathematics with Princeton University, Princeton, NJ, USA, from 2009 to 2010, and a Research Scientist with the Department of Electrical and Computer Engineering, Duke University, Durham, NC, USA, from 2010 to 2011. He has been with Rutgers University, Piscataway, NJ, USA, since 2011, where he is currently an Associate Professor with the Department of Electrical and Computer Engineering and an Associate Member of the graduate faculty of the Department of Statistics. His research interests include statistical signal processing, high-dimensional statistics, machine learning, inverse problems, and networked systems. Dr. Bajwa received the Best in Academics Gold Medal and President’s Gold Medal in Electrical Engineering from the National University of Sciences and Technology in 2001, the Morgridge Distinguished Graduate Fellowship from the University of Wisconsin–Madison in 2003, the Army Research Office Young Investigator Award in 2014, the National Science Foundation CAREER Award in 2015, the Rutgers University’s Presidential Merit Award in 2016, the Rutgers University’s Presidential Fellowship for Teaching Excellence in 2017, and the Rutgers Engineering Governing Council ECE Professor of the Year Award in 2016, 2017, and 2019. He is a co-investigator on a work that received the Cancer Institute of New Jersey’s Gallo Award for Scientific Excellence in 2017, a coauthor on papers that received best student paper awards at IEEE IVMSP 2016 and IEEE CAMSAP 2017 workshops, and a member of the Class of 2015 National Academy of Engineering Frontiers of Engineering Education Symposium. He served as the Lead Guest Editor for the IEEE Signal Processing Magazine —Special Issue on Distributed, Streaming Machine Learning in 2020, the Technical Co-Chair for the IEEE SPAWC 2018 Workshop, the Technical Area Chair of the 2018 Asilomar Conference on Signals, Systems, and Computers, the General Chair for the 2017 DIMACS Workshop on Distributed Optimization, Information Processing, and Learning, and an Associate Editor for IEEE Signal Processing Letters from 2014 to 2017. He is also serving as a Senior Area Editor for IEEE Signal Processing Letters and an Associate Editor for IEEE Transactions on Signal and Information Processing over Networks.

Michael G. Rabbat (Senior Member, IEEE) received the B.Sc. degree from the University of Illinois at Urbana–Champaign, Champaign, IL, USA, in 2001, the M.Sc. degree from Rice University, Houston, TX, USA, in 2003, and the Ph.D. degree from the University of Wisconsin–Madison, Madison, WI, USA, in 2006, all in electrical engineering. He is currently a Research Scientist with the Facebook Artificial Intelligence Research Group (FAIR), Montreal, QC, Canada. From 2007 to 2018, he was a Professor with the Department of Electrical and Computer Engineering, McGill University, Montreal, QC, Canada. From 2013 to 2014, he held visiting positions at Télécom Bretegne, Brest, France, the Inria Bretagne-Atlantique Research Centre, Rennes, France, and the KTH Royal Institute of Technology, Stockholm, Sweden. His research interests include optimization, distributed algorithms, graph signal processing, and machine learning.

Ali H. Sayed (Fellow, IEEE) is the Dean of Engineering with EPFL, Lausanne, Switzerland, where he also leads the Adaptive Systems Laboratory. He served as a Distinguished Professor and the former Chairman of electrical engineering at the University of California at Los Angeles, Los Angeles, CA, USA. He is a member of the U.S. National Academy of Engineering and is recognized as a Highly Cited Researcher by Thomson Reuters and Clarivate Analytics. He is an author of over 570 publications and six books. His research interests include adaptation and learning theories, data and network sciences, statistical inference, optimization, and biologically inspired designs. Prof. Sayed is a Fellow of EURASIP and the American Association for the Advancement of Science (AAAS). His work has been recognized with several awards, including the 2015 Education Award from the IEEE Signal Processing Society, the 2014 Papoulis Award from the European Association for Signal Processing, the 2013 Meritorious Service Award and the 2012 Technical Achievement Award from the IEEE Signal Processing Society, the 2005 Terman Award from the American Society for Engineering Education, the 2005 Distinguished Lecturer from the IEEE Signal Processing Society, the 2003 Kuwait Prize in Basic Sciences, and the 1996 IEEE Fink Prize. He received several best paper awards from the IEEE in 2002, 2005, 2012, and 2014 and EURASIP in 2015. He served as the President of the IEEE Signal Processing Society from 2018 to 2019.