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...
Saved in:
Main Authors: | , , , |
---|---|
Format: | article |
Language: | EN |
Published: |
Hindawi Limited
2021
|
Subjects: | |
Online Access: | https://doaj.org/article/09154e3ff5c64b9a8f24e212323ae4d8 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|