M.D. I. Estimation via Unconstrained Convex Programming.
Abstract
A method is presented for obtaining minimum discrimination information (M.D.I.) estimates of probability distributions. This involves using an extremal principal and, viewing M.D.I. estimation in a dual convex programming framework. The resulting dual convex program is unconstrained and involves only exponential and linear terms, and hence is easily solved. This approach makes M.D.I. estimation computationally efficient and reduces the time and cost of obtaining such estimates.
Document Details
- Document Type
- Technical Report
- Publication Date
- Nov 01, 1978
- Accession Number
- ADA065459
Entities
People
- Abraham Charnes
- Patrick L. Brockett
- William W. Cooper
Organizations
- University of Texas at Austin