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...

Description complète

Enregistré dans:
Détails bibliographiques
Auteurs principaux: Yan Liu, Maojun Zhang, Zhiwei Zhong, Xiangrong Zeng
Format: article
Langue:EN
Publié: Hindawi Limited 2021
Sujets:
Accès en ligne:https://doaj.org/article/09154e3ff5c64b9a8f24e212323ae4d8
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!