Global performance guarantees of second-order methods for unconstrained convex minimization
Pavel, Dvurechensky (pavel.dvurechensky@wias-berlin.de) and
Yurii, Nesterov (yurii.nesterov@uclouvain.be)
Additional contact information
Pavel, Dvurechensky: Weierstrass Institute for Applied Analysis and Stochastics
Yurii, Nesterov: CORE, UCLouvain
No 2018032, LIDAM Discussion Papers CORE from Université catholique de Louvain, Center for Operations Research and Econometrics (CORE)
Abstract:
In this paper we make an attempt to compare two distinct branches of research on second-order optimization methods. The first one studies self-concordant functions and barriers, the main assumption being that the third derivative of the objective is bounded by the second derivative. The second branch studies cubic regularized Newton methods with main assumption that the second derivative is Lipschitz continuous. We develop new theoretical analysis for a path-following scheme for general self-concordant function, as opposed to classical path-following scheme developed for self-concordant barriers. We show that the complexity bound for this scheme is better than for Damped Newton Method. Next, we analyze an important subclass of general self-concordant function, namely a class of strongly convex functions with Lipschitz continuous second derivative and show that for this subclass cubic regularized New Methods give even better complexity bound.
Keywords: self-concordant function; Damped Newton Method; cubic regularized Newton method; path-following method (search for similar items in EconPapers)
Date: 2018-12-07
References: Add references at CitEc
Citations:
Downloads: (external link)
https://sites.uclouvain.be/core/publications/coredp/coredp2018.html (application/pdf)
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:cor:louvco:2018032
Access Statistics for this paper
More papers in LIDAM Discussion Papers CORE from Université catholique de Louvain, Center for Operations Research and Econometrics (CORE) Voie du Roman Pays 34, 1348 Louvain-la-Neuve (Belgium). Contact information at EDIRC.
Bibliographic data for series maintained by Alain GILLIS (alain.gillis@uclouvain.be).