Cargando…
AdaCN: An Adaptive Cubic Newton Method for Nonconvex Stochastic Optimization
In this work, we introduce AdaCN, a novel adaptive cubic Newton method for nonconvex stochastic optimization. AdaCN dynamically captures the curvature of the loss landscape by diagonally approximated Hessian plus the norm of difference between previous two estimates. It only requires at most first o...
Autores principales: | Liu, Yan, Zhang, Maojun, Zhong, Zhiwei, Zeng, Xiangrong |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Hindawi
2021
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8598341/ https://www.ncbi.nlm.nih.gov/pubmed/34804146 http://dx.doi.org/10.1155/2021/5790608 |
Ejemplares similares
-
Data and performance profiles applying an adaptive truncation criterion, within linesearch-based truncated Newton methods, in large scale nonconvex optimization
por: Caliciotti, Andrea, et al.
Publicado: (2018) -
Stochastic proximal gradient methods for nonconvex problems in Hilbert spaces
por: Geiersbach, Caroline, et al.
Publicado: (2021) -
Topics in Nonconvex Optimization
por: Mishra, Shashi Kant
Publicado: (2011) -
Minimizing Uniformly Convex Functions by Cubic Regularization of Newton Method
por: Doikov, Nikita, et al.
Publicado: (2021) -
Duality for nonconvex approximation and optimization
por: Singer, Ivan
Publicado: (2006)