Cargando…
Minimizing Uniformly Convex Functions by Cubic Regularization of Newton Method
In this paper, we study the iteration complexity of cubic regularization of Newton method for solving composite minimization problems with uniformly convex objective. We introduce the notion of second-order condition number of a certain degree and justify the linear rate of convergence in a nondegen...
Autores principales: | Doikov, Nikita, Nesterov, Yurii |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Springer US
2021
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8550329/ https://www.ncbi.nlm.nih.gov/pubmed/34720181 http://dx.doi.org/10.1007/s10957-021-01838-7 |
Ejemplares similares
-
Local convergence of tensor methods
por: Doikov, Nikita, et al.
Publicado: (2021) -
New Results on Superlinear Convergence of Classical Quasi-Newton Methods
por: Rodomanov, Anton, et al.
Publicado: (2021) -
Implementable tensor methods in unconstrained convex optimization
por: Nesterov, Yurii
Publicado: (2019) -
Subgradient ellipsoid method for nonsmooth convex problems
por: Rodomanov, Anton, et al.
Publicado: (2022) -
AdaCN: An Adaptive Cubic Newton Method for Nonconvex Stochastic Optimization
por: Liu, Yan, et al.
Publicado: (2021)