Computer Science Department
School of Computer Science, Carnegie Mellon University
Duality and Auxiliary Functions for Bregman Distances
Stephen Della Pietra, Vincent Della Pietra, John Lafferty
October 2001
This document has been revised and is now superceded by
Computer Science Technical Report CMU-CS-01-109R
published in February 2002.
CMU-CS-01-109.ps
CMU-CS-01-109.pdf
CMU-CS-01-109R.ps
CMU-CS-01-109R.pdf
We formulate and prove a convex duality theorem for Bregman distances
and present a technique based on auxiliary functions for deriving and
proving convergence of iterative algorithms to minimize Bregman
distance subject to linear constraints.
15 pages
Return to:
SCS Technical Report Collection This page maintained by reports@cs.cmu.edu
School of Computer Science homepage