About this document

Yurii Nesterov and Boris T. Polyak, Cubic Regularization of Newton Method and Its Global Performance by Hongqing Yu is a document available to read on EtoBox.

This paper introduces a cubic regularization of the Newton method for unconstrained minimization, providing general convergence results and analyzing its performance across various problem classes. It demonstrates that the search direction can be computed using standard linear algebra techniques and establishes global and local worst-case complexity bounds. The authors argue that their proposed method outperforms traditional gradient methods in terms of convergence rates.

Author

Hongqing Yu

Language

EN