Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2018
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/1805.08204 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910825930817536 |
|---|---|
| author | Josz, Cedric Ouyang, Yi Zhang, Richard Y. Lavaei, Javad Sojoudi, Somayeh |
| author_facet | Josz, Cedric Ouyang, Yi Zhang, Richard Y. Lavaei, Javad Sojoudi, Somayeh |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_1805_08204 |
| institution | arXiv |
| publishDate | 2018 |
| record_format | arxiv |
| spellingShingle | A theory on the absence of spurious solutions for nonconvex and nonsmooth optimization Josz, Cedric Ouyang, Yi Zhang, Richard Y. Lavaei, Javad Sojoudi, Somayeh Optimization and Control 90C26 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. |
| title | A theory on the absence of spurious solutions for nonconvex and nonsmooth optimization |
| topic | Optimization and Control 90C26 |
| url | https://arxiv.org/abs/1805.08204 |