Stochastic Composition Optimization of Functions Without Lipschitz Continuous Gradient

Yin Liu () and Sam Davanloo Tajbakhsh ()
Additional contact information
Yin Liu: The Ohio State University
Sam Davanloo Tajbakhsh: The Ohio State University

Journal of Optimization Theory and Applications, 2023, vol. 198, issue 1, No 10, 239-289

Abstract: Abstract In this paper, we study stochastic optimization of two-level composition of functions without Lipschitz continuous gradient. The smoothness property is generalized by the notion of relative smoothness which provokes the Bregman gradient method. We propose three stochastic composition Bregman gradient algorithms for the three possible relatively smooth compositional scenarios and provide their sample complexities to achieve an $$\epsilon $$ ϵ -approximate stationary point. For the smooth of relatively smooth composition, the first algorithm requires $$\mathcal {O}(\epsilon ^{-2})$$ O ( ϵ - 2 ) calls to the stochastic oracles of the inner function value and gradient as well as the outer function gradient. When both functions are relatively smooth, the second algorithm requires $$\mathcal {O}(\epsilon ^{-3})$$ O ( ϵ - 3 ) calls to the inner function value stochastic oracle and $$\mathcal {O}(\epsilon ^{-2})$$ O ( ϵ - 2 ) calls to the inner and outer functions gradients stochastic oracles. We further improve the second algorithm by variance reduction for the setting where just the inner function is smooth. The resulting algorithm requires $$\mathcal {O}(\epsilon ^{-5/2})$$ O ( ϵ - 5 / 2 ) calls to the inner function value stochastic oracle, $$\mathcal {O}(\epsilon ^{-3/2})$$ O ( ϵ - 3 / 2 ) calls to the inner function gradient, and $$\mathcal {O}(\epsilon ^{-2})$$ O ( ϵ - 2 ) calls to the outer function gradient stochastic oracles. Finally, we numerically evaluate the performance of these three algorithms over two different examples.

Keywords: Composition optimization; Stochastic optimization algorithm; Bregman subproblem (search for similar items in EconPapers)
Date: 2023
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1007/s10957-023-02180-w 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:198:y:2023:i:1:d:10.1007_s10957-023-02180-w

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

DOI: 10.1007/s10957-023-02180-w

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 ().