Skip to main content
U.S. Department of Energy
Office of Scientific and Technical Information

Exact and inexact subsampled Newton methods for optimization

Journal Article · · IMA Journal of Numerical Analysis
 [1];  [2];  [2]
  1. Department of Industrial Engineering and Management Sciences, Northwestern University, Evanston, IL, USA
  2. Department of Computer Science, University of Colorado, Boulder, CO, USA

Abstract

The paper studies the solution of stochastic optimization problems in which approximations to the gradient and Hessian are obtained through subsampling. We first consider Newton-like methods that employ these approximations and discuss how to coordinate the accuracy in the gradient and Hessian to yield a superlinear rate of convergence in expectation. The second part of the paper analyzes an inexact Newton method that solves linear systems approximately using the conjugate gradient (CG) method, and that samples the Hessian and not the gradient (the gradient is assumed to be exact). We provide a complexity analysis for this method based on the properties of the CG iteration and the quality of the Hessian approximation, and compare it with a method that employs a stochastic gradient iteration instead of the CG method. We report preliminary numerical results that illustrate the performance of inexact subsampled Newton methods on machine learning applications based on logistic regression.

Research Organization:
Northwestern Univ., Evanston, IL (United States)
Sponsoring Organization:
USDOE Office of Science (SC)
DOE Contract Number:
FG02-87ER25047
OSTI ID:
1610078
Journal Information:
IMA Journal of Numerical Analysis, Vol. 39, Issue 2; ISSN 0272-4979
Publisher:
Oxford University Press/Institute of Mathematics and its Applications
Country of Publication:
United States
Language:
English

References (11)

Simulation optimization: a review of algorithms and applications journal November 2014
Comparative accuracies of artificial neural networks and discriminant analysis in predicting forest cover types from cartographic variables journal December 1999
On-line learning for very large data sets journal January 2005
Sample size selection in optimization methods for machine learning journal June 2012
Inexact Newton Methods journal April 1982
Hybrid Deterministic-Stochastic Methods for Data Fitting journal January 2012
Efficient least-squares imaging with sparsity promotion and compressive sensing: Compressive imaging journal January 2012
Training Deep and Recurrent Networks with Hessian-Free Optimization book January 2012
Parallel Boosting with Momentum book January 2013
Numerical Optimization book January 1999
Computational Methods for Sparse Solution of Linear Inverse Problems journal June 2010

Related Subjects