Sebastian Pokutta: "Structured ML Training via Conditional Gradients" скачать в хорошем качестве

Sebastian Pokutta: "Structured ML Training via Conditional Gradients"

Deep Learning and Combinatorial Optimization 2021 "Structured ML Training via Conditional Gradients" Sebastian Pokutta - Konrad-Zuse-Zentrum für Informationstechnik (ZIB), Department of Mathematics Abstract: Conditional Gradient methods are an important class of methods to minimize (non-)smooth convex functions over (combinatorial) 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. Institute for Pure and Applied Mathematics, UCLA February 23, 2021 For more information: https://www.ipam.ucla.edu/dlc2021​