Friday, Novemberg 20, 2020, 2:30pm
Conditional Gradients in Machine Learning and Optimization
Sebastian Pokutta (Zuse Institute Berlin, http://www.pokutta.com/)
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.
Die Vorträge finden aufgrund der Corona-Pandemie in diesem Semester über Zoom statt.
ID 952 6037 6553