Sciweavers

Free Online Productivity Tools i2Speak i2Symbol i2OCR iTex2Img iWeb2Print iWeb2Shot i2Type iPdf2Split iPdf2Merge i2Bopomofo i2Arabic i2Style i2Image i2PDF iLatex2Rtf Sci2ools

5

MP
2006

favoriteEmaildiscussreport

134views more MP 2006»

Cubic regularization of Newton method and its global performance

13 years 4 months ago

Cubic regularization of Newton method and its global performance

Download www.core.ucl.ac.be

In this paper, we provide theoretical analysis for a cubic regularization of Newton method as applied to unconstrained minimization problem. For this scheme, we prove general local convergence results. However, the main contribution of the paper is related to global worst-case complexity bounds for different problem classes including some nonconvex cases. It is shown that the search direction can be computed by standard linear algebra technique.

Yurii Nesterov, Boris T. Polyak

Real-time Traffic

Cubic Regularization | Global Worst-case Complexity | MP 2006 | Unconstrained Minimization Problem |

claim paper

Related Content

» Accelerating the cubic regularization of Newtons method on convex problems

» A QuasiNewton Approach to Nonsmooth Convex Optimization Problems in Machine Learning

» Scalable training of L1regularized loglinear models

» Minimization of a DetailPreserving Regularization Functional for Impulse Noise Removal

» Newtonian clustering An approach based on molecular dynamics and global optimization

» An adaptive bin framework search method for a betasheet protein homopolymer model

» ArrayBased QRRLS Multichannel Lattice Filtering

» A BoxConsistency Contractor Based on Extremal Functions

» A Unified Framework Based on the Level Set Approach for Segmentation of Unconstrained Doub...

Post Info
More Details (n/a)

Added	14 Dec 2010
Updated	14 Dec 2010
Type	Journal
Year	2006
Where	MP
Authors	Yurii Nesterov, Boris T. Polyak

Comments (0)