A theory on the absence of spurious solutions for nonconvex and nonsmooth optimization

Abstract

We study the set of continuous functions that admit no spurious local optima (i.e. local minima that are not global minima) which we term \textit{global functions}. They satisfy various powerful properties for analyzing nonconvex and nonsmooth optimization problems. For instance, they satisfy a theorem akin to the fundamental uniform limit theorem in the analysis regarding continuous functions. Global functions are also endowed with useful properties regarding the composition of functions and change of variables. Using these new results, we show that a class of nonconvex and nonsmooth optimization problems arising in tensor decomposition applications are global functions. This is the first result concerning nonconvex methods for nonsmooth objective functions. Our result provides a theoretical guarantee for the widely-used ${\ell }_1$ norm to avoid outliers in nonconvex optimization.

arXiv comment22 pages, 13 figures

Cited by in corpus (5)

• On the Benefit of Width for Neural Networks: Disappearance of Bad Basins
• Nonconvex Robust Low-rank Matrix Recovery
• Escaping spurious local minimum trajectories in online time-varying nonconvex optimization
• About some works of Boris Polyak on convergence of gradient methods and their development
• Sign-RIP: A Robust Restricted Isometry Property for Low-rank Matrix Recovery