7 May – Sebastian Pokutta: Conditional Gradients in Machine Learning and Optimization
Conditional Gradient Methods are an important class of methods to minimize smooth convex functions over polytopes. Recently, these methods have received a lot of attention as they allow for structured optimization and hence learning, incorporating the underlying polyhedral structure into solutions.
In this talk, Pokutta will give a broad overview of these methods and their applications and present some recent results both in traditional optimization and learning as well as in deep learning.
Sebastian Pokutta is the Vice President of the Zuse Institute Berlin (ZIB) and a Professor of Mathematics at TU Berlin with a research focus on Artificial Intelligence and Optimization. After receiving his Ph.D. in mathematics from the University of Duisburg-Essen, Pokutta was a postdoctoral researcher and visiting lecturer at MIT. Prior to joining ZIB and TU Berlin, he was the David M. McKenney Family Associate Professor in the School of Industrial and Systems Engineering and an Associate Director of the Machine Learning at GT Center at the Georgia Institute of Technology as well as a Professor at the University of Erlangen-Nürnberg. He also received an NSF CAREER Award in 2015 and the David M. McKenney Family Early Career Professorship in 2016.
