Learning Convex Sets of Probability from Data

Fabio Cozman and Lonnie Chrisman
tech. report CMU-RI-TR-97-25, Robotics Institute, Carnegie Mellon University, July, 1997


Download
  • Adobe portable document format (pdf) (203KB)
Copyright notice: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.

Abstract
Several theories of inference and decision employ sets of probability distributions as the fundamental representation of (subjective) belief. This paper investigates a frequentist connection between empirical data and convex sets of probability distributions. Building on earlier work by Walley and Fine, a framework is advanced in which a sequence of random outcomes can be described as being drawn from a convex set of distributions, rather than just from a single distribution. The extra generality can be detected from observable characteristics of the outcome sequence. The paper presents new asymptotic convegence results paralleling the laws of large numbers in probability theory, and concludes with a comparison between this approach and approaches based on prior subjective constraints.

Notes
Sponsor: NASA, CNPq
Grant ID: NAGW-1175
Number of pages: 18

Text Reference
Fabio Cozman and Lonnie Chrisman, "Learning Convex Sets of Probability from Data," tech. report CMU-RI-TR-97-25, Robotics Institute, Carnegie Mellon University, July, 1997

BibTeX Reference
@techreport{Cozman_1997_450,
   author = "Fabio Cozman and Lonnie Chrisman",
   title = "Learning Convex Sets of Probability from Data",
   booktitle = "",
   institution = "Robotics Institute",
   month = "July",
   year = "1997",
   number= "CMU-RI-TR-97-25",
   address= "Pittsburgh, PA",
}