Examples of Pathological Dynamics of the Subgradient Method for Lipschitz Path-Differentiable Functions

Rodolfo Ríos-Zertuche ()
Additional contact information
Rodolfo Ríos-Zertuche: Laboratoire d’Analyse et d’Architecture des Systèmes du CNRS, 31031 Toulouse, France

Mathematics of Operations Research, 2022, vol. 47, issue 4, 3184-3206

Abstract: We show that the vanishing step size subgradient method—widely adopted for machine learning applications—can display rather messy behavior even in the presence of favorable assumptions. We establish that convergence of bounded subgradient sequences may fail even with a Whitney stratifiable objective function satisfying the Kurdyka-Łojasiewicz inequality. Moreover, when the objective function is path-differentiable, we show that various properties all may fail to occur: criticality of the limit points, convergence of the sequence, convergence in values, codimension one of the accumulation set, equality of the accumulation and essential accumulation sets, connectedness of the essential accumulation set, spontaneous slowdown, oscillation compensation, and oscillation perpendicularity to the accumulation set.

Keywords: Primary: 65K10; secondary: 37A50; 37B35; large-scale optimization; gradient descent (search for similar items in EconPapers)
Date: 2022
References: Add references at CitEc
Citations:

Downloads: (external link)
http://dx.doi.org/10.1287/moor.2021.1241 (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:inm:ormoor:v:47:y:2022:i:4:p:3184-3206

Access Statistics for this article

More articles in Mathematics of Operations Research from INFORMS Contact information at EDIRC.
Bibliographic data for series maintained by Chris Asher ().