An Active Set Limited Memory BFGS Algorithm for Machine Learning

An Active Set Limited Memory BFGS Algorithm for Machine Learning

In this paper, a stochastic quasi-Newton algorithm for nonconvex stochastic optimization is presented. It is derived from a classical modified BFGS formula. The update formula can be extended to the framework of limited memory scheme. Numerical experiments on some problems in machine learning are gi...

Full description

Bibliographic Details
Main Authors: Hanger Liu, Yan Li, Maojun Zhang
Format: Article
Language:English
Published: MDPI AG 2022-02-01
Series:Symmetry
Subjects:
nonconvex stochastic optimization
stochastic approximation
quasi-Newton method
damped limited-memory BFGS method
variance reduction
Online Access:https://www.mdpi.com/2073-8994/14/2/378

Internet

https://www.mdpi.com/2073-8994/14/2/378

Similar Items