Combining Stochastic Adaptive Cubic Regularization with Negative Curvature for Nonconvex Optimization

Seonho Park (), Seung Hyun Jung () and Panos M. Pardalos ()
Additional contact information
Seonho Park: University of Florida
Seung Hyun Jung: Korea Institute of Industrial Technology (KITECH)
Panos M. Pardalos: University of Florida

Journal of Optimization Theory and Applications, 2020, vol. 184, issue 3, No 12, 953-971

Abstract: Abstract We focus on minimizing nonconvex finite-sum functions that typically arise in machine learning problems. In an attempt to solve this problem, the adaptive cubic-regularized Newton method has shown its strong global convergence guarantees and the ability to escape from strict saddle points. In this paper, we expand this algorithm to incorporating the negative curvature method to update even at unsuccessful iterations. We call this new method Stochastic Adaptive cubic regularization with Negative Curvature (SANC). Unlike the previous method, in order to attain stochastic gradient and Hessian estimators, the SANC algorithm uses independent sets of data points of consistent size over all iterations. It makes the SANC algorithm more practical to apply for solving large-scale machine learning problems. To the best of our knowledge, this is the first approach that combines the negative curvature method with the adaptive cubic-regularized Newton method. Finally, we provide experimental results, including neural networks problems supporting the efficiency of our method.

Keywords: Adaptive cubic-regularized Newton method; Cubic regularization; Trust-region method; Negative curvature; Nonconvex optimization; Worst-case complexity; 49M05; 49M15; 90C06; 90C15; 90C60 (search for similar items in EconPapers)
Date: 2020
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (1)

Downloads: (external link)
http://link.springer.com/10.1007/s10957-019-01624-6 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:184:y:2020:i:3:d:10.1007_s10957-019-01624-6

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

DOI: 10.1007/s10957-019-01624-6

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 ().