English

When Are Nonconvex Problems Not Scary?

Optimization and Control 2016-04-26 v2 Information Theory math.IT Machine Learning

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.

Keywords

Cite

@article{arxiv.1510.06096,
  title  = {When Are Nonconvex Problems Not Scary?},
  author = {Ju Sun and Qing Qu and John Wright},
  journal= {arXiv preprint arXiv:1510.06096},
  year   = {2016}
}

Comments

6 pages, 3 figures. New examples on phase synchronization and community detection added; emphasis on all local minimizers being global added; exposition is polished. This is a concise expository article that avoids much technical rigor. We will make a separate submission with full technical details in future

R2 v1 2026-06-22T11:25:11.797Z