When Are Nonconvex Problems Not Scary?

Author name not available (Why is that?)

Publication date: 20 October 2015

Abstract: In this note, we focus on smooth nonconvex optimization problems that obey: (1) all local minimizers are also global; and (2) around any saddle point or local maximizer, the objective has a negative directional curvature. Concrete applications such as dictionary learning, generalized phase retrieval, and orthogonal tensor decomposition are known to induce such structures. We describe a second-order trust-region algorithm that provably converges to a global minimizer efficiently, without special initializations. Finally we highlight alternatives, and open problems in this direction.

Has companion code repository: https://github.com/SKorablyov/MaxProblem

This page was built for publication: When Are Nonconvex Problems Not Scary?

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6266614)