Timezone: »

Submodular Optimization and Nonconvexity
Stefanie Jegelka

Fri Dec 09 04:30 AM -- 05:00 AM (PST) @ None

Despite analogies of submodularity and convexity, submodular optimization is closely connected with certain "nice" non-convex optimization problems for which theoretical guarantees are still possible. In this talk, I will review some of these connections and make them specific at the example of a challenging robust influence maximization problem, for which we obtain new, tractable formulations and algorithms.

Author Information

Stefanie Jegelka (MIT)

Stefanie Jegelka is an X-Consortium Career Development Assistant Professor in the Department of EECS at MIT. She is a member of the Computer Science and AI Lab (CSAIL), the Center for Statistics and an affiliate of the Institute for Data, Systems and Society and the Operations Research Center. Before joining MIT, she was a postdoctoral researcher at UC Berkeley, and obtained her PhD from ETH Zurich and the Max Planck Institute for Intelligent Systems. Stefanie has received a Sloan Research Fellowship, an NSF CAREER Award, a DARPA Young Faculty Award, the German Pattern Recognition Award and a Best Paper Award at the International Conference for Machine Learning (ICML). Her research interests span the theory and practice of algorithmic machine learning.

More from the Same Authors