Talk
in
Workshop: Nonconvex Optimization for Machine Learning: Theory and Practice

Submodular Optimization and Nonconvexity

Stefanie Jegelka

2016 Talk
in
Workshop: Nonconvex Optimization for Machine Learning: Theory and Practice

Abstract

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.

Chat is not available.