Open for all UnRAVeL Members: Sebastian Pokutta: Conditional Gradients in Machine Learning and Optimization

Friday, November 20, 2020, 2:30pm

Location: online session

Speaker: Prof. Sebastian Pokutta (Zuse Institute Berlin)

 

Abstract: 

Conditional Gradient methods are an important class of methods to minimize smooth convex functions over polytopes. Recently these methods received a lot of attention as they allow for structured optimization and hence learning, incorporating the underlying polyhedral structure into solutions. In this talk I will give a broad overview of these methods, their applications, as well as present some recent results both in traditional optimization and learning as well as in deep learning.