Stochastic zeroth order descent with structured directions
Marco Rando (),
Cesare Molinari (),
Silvia Villa () and
Lorenzo Rosasco ()
Additional contact information
Marco Rando: University of Genoa
Cesare Molinari: University of Genoa
Silvia Villa: University of Genoa
Lorenzo Rosasco: University of Genoa
Computational Optimization and Applications, 2024, vol. 89, issue 3, No 5, 727 pages
Abstract:
Abstract We introduce and analyze Structured Stochastic Zeroth order Descent (S-SZD), a finite difference approach that approximates a stochastic gradient on a set of $$l\le d$$ l ≤ d orthogonal directions, where d is the dimension of the ambient space. These directions are randomly chosen and may change at each step. For smooth convex functions we prove almost sure convergence of the iterates and a convergence rate on the function values of the form $$O( (d/l) k^{-c})$$ O ( ( d / l ) k - c ) for every $$c
Keywords: Zeroth-order optimization; Finite differences; Black-box optimization; Derivative-free optimization; Stochastic optimization; Convex optimization; 90C56; 90C15; 90C25; 90C30 (search for similar items in EconPapers)
Date: 2024
References: View references in EconPapers View complete reference list from CitEc
Citations:
Downloads: (external link)
http://link.springer.com/10.1007/s10589-024-00616-1 Abstract (text/html)
Access to the full text of the articles in this series is restricted.
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:spr:coopap:v:89:y:2024:i:3:d:10.1007_s10589-024-00616-1
Ordering information: This journal article can be ordered from
http://www.springer.com/math/journal/10589
DOI: 10.1007/s10589-024-00616-1
Access Statistics for this article
Computational Optimization and Applications is currently edited by William W. Hager
More articles in Computational Optimization and Applications from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().