Zeroth-Order Random Subspace Algorithm for Non-smooth Convex Optimization

Ryota Nozawa (), Pierre-Louis Poirion () and Akiko Takeda ()
Additional contact information
Ryota Nozawa: The University of Tokyo
Pierre-Louis Poirion: RIKEN
Akiko Takeda: The University of Tokyo

Journal of Optimization Theory and Applications, 2025, vol. 204, issue 3, No 18, 31 pages

Abstract: Abstract Zeroth-order optimization, which does not use derivative information, is one of the significant research areas in the field of mathematical optimization and machine learning. Although various studies have explored zeroth-order algorithms, one of the theoretical limitations is that oracle complexity depends on the dimension, i.e., on the number of variables, of the optimization problem. In this paper, to reduce the dependency of the dimension in oracle complexity, we propose a zeroth-order random subspace algorithm by combining a gradient-free algorithm (specifically, Gaussian randomized smoothing with central differences) with random projection. We derive the worst-case oracle complexity of our proposed method in non-smooth and convex settings; it is equivalent to standard results for full-dimensional non-smooth convex algorithms. Furthermore, we prove that ours also has a local convergence rate independent of the original dimension under additional assumptions. In addition to the theoretical results, numerical experiments show that when an objective function has a specific structure, the proposed method can become experimentally more efficient due to random projection.

Keywords: Zeroth-order optimization; Random projection; Convex optimization; Oracle complexity; 49J52; 60B20; 90C06; 90C25; 90C56 (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/s10957-024-02561-9 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:204:y:2025:i:3:d:10.1007_s10957-024-02561-9

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

DOI: 10.1007/s10957-024-02561-9

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 ().