Accelerated gradient sliding for structured convex optimization

Guanghui Lan () and Yuyuan Ouyang ()
Additional contact information
Guanghui Lan: Georgia Institute of Technology
Yuyuan Ouyang: Clemson University

Computational Optimization and Applications, 2022, vol. 82, issue 2, No 3, 394 pages

Abstract: Abstract Our main goal in this paper is to show that one can skip gradient computations for gradient descent type methods applied to certain structured convex programming (CP) problems. To this end, we first present an accelerated gradient sliding (AGS) method for minimizing the summation of two smooth convex functions with different Lipschitz constants. We show that the AGS method can skip the gradient computation for one of these smooth components without slowing down the overall optimal rate of convergence. This result is much sharper than the classic black-box CP complexity results especially when the difference between the two Lipschitz constants associated with these components is large. We then consider an important class of bilinear saddle point problem whose objective function is given by the summation of a smooth component and a nonsmooth one with a bilinear saddle point structure. Using the aforementioned AGS method for smooth composite optimization and Nesterov’s smoothing technique, we show that one only needs $${{\mathcal{O}}}(1/\sqrt{\varepsilon })$$ O ( 1 / ε ) gradient computations for the smooth component while still preserving the optimal $${{\mathcal{O}}}(1/\varepsilon )$$ O ( 1 / ε ) overall iteration complexity for solving these saddle point problems. We demonstrate that even more significant savings on gradient computations can be obtained for strongly convex smooth and bilinear saddle point problems.

Keywords: Convex programming; Accelerated gradient sliding; Structure; Complexity; Nesterov’s method; 90C25; 90C06; 49M37 (search for similar items in EconPapers)
Date: 2022
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1007/s10589-022-00365-z 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:82:y:2022:i:2:d:10.1007_s10589-022-00365-z

Ordering information: This journal article can be ordered from
http://www.springer.com/math/journal/10589

DOI: 10.1007/s10589-022-00365-z

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 ().