Prof. Sebastian Pokutta, Ph.D., Atlanta
January 19, 11.00: Digital World
Machine Learning and Decision-making in the Real-World
Machine Learning and Decision-Making have been very successful recently in addressing and solving a large number of open problems and real-word challenges. Some prominent examples include Deepmind’s recent success with AlphaGo, breakthrough super-human performance in computer vision using deep convolutional neural networks, and generative adversarial networks to enable learning systems that improve by playing against each other.
In this talk I will survey recent progress in Machine Learning and Decision-Making and its impact on innovation and real-world problem solving as well as challenges and risks of using these technologies. I will then present some recent results from reinforcement learning under model mismatch, where the training environment can differ from the deployment environment.
About Prof. Sebastian Pokutta
Sebastian Pokutta is the David M. McKenney Family Associate Professor in the School of Industrial and Systems Engineering and an Associate Director of the Machine Learning @ GT Center at the Georgia Insitute of Technology. Having received both his diploma and Ph.D. in mathematics from the University of Duisburg-Essen in Germany, Pokutta was a postdoctoral researcher and visiting lecturer at MIT, worked for IBM ILOG, and Krall Demmel Baumgarten. Prior to joining the Georgia Institute of Technology, he was a Professor at the University of Erlangen-Nürnberg. Sebastian received the David M. McKenney Family Early Career Professorship in 2016, an NSF CAREER Award in 2015, the Coca-Cola Early Career Professorship in 2014, the outstanding thesis award of the University of Duisburg-Essen in 2006, as well as various Best Paper awards. Pokutta’s primary research interests are in optimization and machine learning in the context of polyhedral combinatorics, in particular extended formulations and continuous optimization techniques as well as analytics with a focus on real-world applications, both in established industries as well as in emerging technologies. Application areas include but are not limited to supply chain management, finance, cyber-physical systems, and predictive analytics.