Index

Lecture series are sponsored by

Prof. Cem Tekin (Bilkent)

Abstract: Recommender systems, dynamic pricing, medical diagnosis, etc., require on-going learning and decision-making in real time. These – and many others – represent perfect examples of the opportunities and difficulties present in sequential decision making under uncertainty: the available information often arrives from a variety of sources and has diverse features so that learning from all the sources may be valuable but integrating what is learned is subject to the curse of dimensionality. Over the last decade, multi-armed bandits became the de facto standard to tackle these problems. I will start this talk by reviewing the Bayesian and frequentist views of the multi-armed bandit problem. Then, I will present recent pieces of multi-armed bandit formulations addressing the aforementioned challenges. The first is about learning and exploiting the information relevant to each action, when the information available at each decision step is high dimensional but the most relevant information is embedded into only a few relevant dimensions. If these relevant dimensions were known in advance, the problem would be simple – but they are not. Moreover, the relevant dimensions may be different for different actions. The second concerns promoting cooperation among informationally decentralized learners that learn how to act on heterogeneous streams of information.

Short Bio: Dr. Cem Tekin is an Assistant Professor in Electrical and Electronics Engineering Department, Bilkent University. He received his PhD degree in Electrical Engineering: Systems from the University of Michigan in 2013. He also received his MS degree in Applied Mathematics and MSE degree in Electrical Engineering: Systems, from the University of Michigan in 2011 and 2010, respectively. Prior to attending the University of Michigan, He received his BS in Electrical and Electronics Engineering (valedictorian) from METU in 2008. From February 2013 to January 2015 he was a postdoctoral scholar in Electrical Engineering Department, UCLA. He received the University of Michigan Electrical Engineering Departmental Fellowship in 2008, and the Fred W. Ellersick award for the best paper in MILCOM 2009. Dr. Tekin's research spans the area of machine learning, data mining and game theory, with an emphasis on online learning and multi-armed bandit problems. His interests lie in both developing the theory in these areas and applying these findings in real-world engineering systems. Specifically, he considers online learning problems in Big Data with applications including real-time stream mining, social recommender systems, healthcare informatics and web-based education.