COMPARATIVE PERFORMANCE ANALYSIS OF SOME ACCELERATED AND HYBRID ACCELERATED GRADIENT MODELS
Authors
Milena Petrović
Faculty of mathematics and natural sciences, University of Priština, Kosovska Mitrovica
Milica Ivanović
Faculty of Natural Sciences and Mathematics, University of Priština, Kosovska Mitrovica, Serbia
Marijana Đorđević
Faculty of mathematics and natural sciences, University of Priština, Kosovska Mitrovica
Keywords
Gradient descent methods, Line search, Convergence rate
Abstract
We analyze a performance profile of several accelerated and hybrid accelerated methods. All comparative methods are at least linearly convergent and have satisfied numerical characteristics regarding tested metrics: number of iterations, CPU time and number of function evaluations. Among the chosen set of methods we numerically show which one is the most efficient and the most effective. Therewith, we derived a conclusion about what type of method is more preferable to use considering analyzed metrics.
Issue
Vol. 9 No. 1 (2019)
Cite this article
CheckingCitation styles are being prepared.