A Randomized Algorithm for Nonconvex Minimization With Inexact Evaluations and Complexity Guarantees

Shuyao Li () and Stephen J. Wright ()
Additional contact information
Shuyao Li: University of Wisconsin–Madison
Stephen J. Wright: University of Wisconsin–Madison

Journal of Optimization Theory and Applications, 2025, vol. 207, issue 3, No 26, 27 pages

Abstract: Abstract We consider minimization of a smooth nonconvex function with inexact oracle access to gradient and Hessian (without assuming access to the function value) to achieve approximate second-order optimality. A novel feature of our method is that if an approximate direction of negative curvature is chosen as the step, we choose its sign to be positive or negative with equal probability. We allow gradients to be inexact (with a bound on their error relative to the size of the true quantity) and relax the coupling between inexactness thresholds for the first- and second-order optimality conditions. Our convergence analysis includes both an expectation bound based on martingale analysis and a high-probability bound based on concentration inequalities. We apply our algorithm to empirical risk minimization problems and obtain improved gradient sample complexity over existing works.

Keywords: Nonconvex optimization; Second-order methods; Second-order stationarity; Inexact gradient; Inexact Hessian; 90C26; 90C17; 68W20 (search for similar items in EconPapers)
Date: 2025
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1007/s10957-025-02817-y 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:joptap:v:207:y:2025:i:3:d:10.1007_s10957-025-02817-y

Ordering information: This journal article can be ordered from
http://www.springer. ... cs/journal/10957/PS2

DOI: 10.1007/s10957-025-02817-y

Access Statistics for this article

Journal of Optimization Theory and Applications is currently edited by Franco Giannessi and David G. Hull

More articles in Journal of Optimization Theory and Applications from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().