Optimization Online


An Inexact Regularized Newton Framework with a Worst-Case Iteration Complexity of $\mathcal{O}(\epsilon^{-3/2})$ for Nonconvex Optimization

Frank E. Curtis(frank.e.curtis***at***gmail.com)
Daniel P. Robinson(daniel.p.robinson***at***gmail.com)
Mohammadreza Samadi(mos213***at***lehigh.edu)

Abstract: An algorithm for solving smooth nonconvex optimization problems is proposed that, in the worst-case, takes $\mathcal{O}(\epsilon^{-3/2})$ iterations to drive the norm of the gradient of the objective function below a prescribed positive real number $\epsilon$ and can take $\mathcal{O}(\epsilon^{-3})$ iterations to drive the leftmost eigenvalue of the Hessian of the objective above $-\epsilon$. The proposed algorithm is a general framework that covers a wide range of techniques including quadratically and cubically regularized Newton methods, such as the Adaptive Regularisation using Cubics (ARC) method, and the recently proposed Trust-Region Algorithm with Contractions and Expansions (TRACE). The generality of our method is achieved through the introduction of generic conditions that each trial step is required to satisfy, which in particular allow for inexact regularized Newton steps to be used. These conditions center around a new subproblem that can be approximately solved to obtain trial steps that satisfy the conditions. For concreteness, an instance of the framework is described that may be viewed as a hybrid between quadratically and cubically regularized Newton methods. Numerical results demonstrate that our hybrid algorithm outperforms a cublicly regularized Newton method.

Keywords: unconstrained optimization, nonlinear optimization, nonconvex optimization, inexact Newton methods, worst-case iteration complexity, worst-case evaluation complexity

Category 1: Nonlinear Optimization

Category 2: Nonlinear Optimization (Unconstrained Optimization )

Citation: Lehigh ISE/COR@L Technical Report 17T-011

Download: [PDF]

Entry Submitted: 09/27/2017
Entry Accepted: 09/27/2017
Entry Last Modified: 09/27/2017

Modify/Update this entry

  Visitors Authors More about us Links
  Subscribe, Unsubscribe
Digest Archive
Search, Browse the Repository


Coordinator's Board
Classification Scheme
Give us feedback
Optimization Journals, Sites, Societies
Mathematical Optimization Society