Leveraging Side-Information for Learning and Optimization under Uncertainty with Aplications in Social and Communication Networks


    Atilla Eryilmaz is a Professor of Electrical and Computer Engineering at The Ohio State University, where he has been a faculty since 2007. He received his M.S. and Ph.D. degrees in Electrical and Computer Engineering from the University of Illinois at Urbana-Champaign in 2001 and 2005, respectively. Between 2005 and 2007, he worked as a Postdoctoral Associate at the Laboratory for Information and Decision Systems (LIDS) at the Massachusetts Institute of Technology. 

    Dr. Eryilmaz's research interests span optimal control of stochastic networks, learning, optimization theory, and information theory. He received the NSF-CAREER Award in 2010 and two Lumley Research Awards for Research Excellence in 2010 and 2015. He is a co-author of the 2012 IEEE WiOpt Conference Best Student Paper, and subsequently received the 2016 IEEE Infocom, 2017 IEEE WiOpt, 2018 IEEE WiOpt, and 2019 IEEE Infocom Conference Best Paper Awards. 


    A recurring problem in the efficient control of networked systems is the need to operate under uncertainty of critical system dynamics. It is usually necessary to develop mechanisms that optimize the target performance measures while also allocating part of their available resources to learning the uncertainties. Optimization of this, learning (exploration) - earning (exploitation) tradeoff has formed the core of many interesting approaches over the last decade that build over the multi-armed bandit (MAB) framework. 

    An important challenge in this research space is concerned with the modeling and utilization of side-information that is typically available about other arms when an arm is pulled. Numerous applications, ranging from social to communication networks, possess different forms of side-information structures, which call for new learning and optimization mechanisms that utilize them for provably low-regret performance guarantees. 

    In this talk, I will provide our research findings from multiple domains, including advertising in social networks, delay-constrained multi-channel communication, and multi-armed bandits for renewal processes, that reveal the gains and means of utilizing various forms of side-information in the optimal learning and control of networks under uncertainty.