This is the program for the 2010 Joint Statistical Meetings in Vancouver, British Columbia.

Abstract Details

Activity Number: 106
Type: Invited
Date/Time: Monday, August 2, 2010 : 8:30 AM to 10:20 AM
Sponsor: International Association for Statistical Computing
Abstract - #305988
Title: Global Regularization Under Constraints
Author(s): Patrick Laurie Davies*+
Companies: University of Duisburg-Essen
Address: , Essen, 45117, Germany
Keywords: global regularization ; multiscale constraints ; linear programming ; sparsity
Abstract:

Many methods used in semi-parametric regression are local in the manner in which the reconstruction is calculated. However If for examples a reconstruction is required to be non-decreasing then it cannot be local as it is required to satisfy a global constraint. Some form of global regularization will, in itself, not solve the problem as the resulting reconstruction may well not be consistent with the data. One way of preventing the solution from moving too far from the data is to impose constraints on the solution and then to regularize subject to these constraints. In general it will be necessary to impose many constraints in order to prevent local and global deviations from the data. This gives rise to optimization problems where the number of constraints is often much larger that the sample size of the data. Algorithmic problems then pose limits on size of data set


The address information is for the authors that have a + after their name.
Authors who are presenting talks have a * after their name.

Back to the full JSM 2010 program




2010 JSM Online Program Home

For information, contact jsm@amstat.org or phone (888) 231-3473.

If you have questions about the Continuing Education program, please contact the Education Department.