Back to Search
Start Over
Proximal Methods Avoid Active Strict Saddles of Weakly Convex Functions.
- Source :
-
Foundations of Computational Mathematics . Apr2022, Vol. 22 Issue 2, p561-606. 46p. - Publication Year :
- 2022
-
Abstract
- We introduce a geometrically transparent strict saddle property for nonsmooth functions. This property guarantees that simple proximal algorithms on weakly convex problems converge only to local minimizers, when randomly initialized. We argue that the strict saddle property may be a realistic assumption in applications, since it provably holds for generic semi-algebraic optimization problems. [ABSTRACT FROM AUTHOR]
- Subjects :
- *ALGORITHMS
Subjects
Details
- Language :
- English
- ISSN :
- 16153375
- Volume :
- 22
- Issue :
- 2
- Database :
- Academic Search Index
- Journal :
- Foundations of Computational Mathematics
- Publication Type :
- Academic Journal
- Accession number :
- 156749210
- Full Text :
- https://doi.org/10.1007/s10208-021-09516-w