An Approximate Nonmyopic Computation for Value of Information

From Tetherless World Wiki

Jump to: navigation, search

Citation: David Heckerman and Eric Horvitz and Blackford Middleton. (1991) An Approximate Nonmyopic Computation for Value of Information. In KSL-91-15, 1991.

Publication techreport ( Edit )
type Technical Report
bibtype techreport
Bibtex basics
author David Heckerman and Eric Horvitz and Blackford Middleton
title An Approximate Nonmyopic Computation for Value of Information
number KSL-91-15
institution Knowledge Systems, AI Laboratory
address University of California, Los Angeles
year 1991
Bibtex more
Access Paper
abstract Value-of-information analyses provide a straightforward means for selecting the best next observation to make, and for determining whether it is better to gather additional information or to act immediately. Determining the next best test to perform, given a state of uncertainty about the world, requires a consideration of the value of making all possible sequences of observations. In practice, decision analysts and expert-system designers have avoided the intractability of exact computation of the value of information by relying on a myopic approximation. Myopic analyses are based on the assumption that only one additional test will be performed, even when there is an opportunity to make a large number of observations. We present a nonmyopic approximation for value of information that bypasses the traditional myopic analyses by exploiting the statistical properties of large samples.

KSL Technical Report ID: KSL-91-15
Facts about An Approximate Nonmyopic Computation for Value of InformationRDF feed
Abstract Value-of-information analyses provide a st … Value-of-information analyses provide a straightforward means for selecting the best next observation to make, and for determining whether it is better to gather additional information or to act immediately. Determining the next best test to perform, given a state of uncertainty about the world, requires a consideration of the value of making all possible sequences of observations. In practice, decision analysts and expert-system designers have avoided the intractability of exact computation of the value of information by relying on a myopic approximation. Myopic analyses are based on the assumption that only one additional test will be performed, even when there is an opportunity to make a large number of observations. We present a nonmyopic approximation for value of information that bypasses the traditional myopic analyses by exploiting the statistical properties of large samples. e statistical properties of large samples.
Address University of California, Los Angeles  +
Author David Heckerman and Eric Horvitz and Blackford Middleton  +
Bibtype techreport  +
Has author David Heckerman and Eric Horvitz and Blackford Middleton  +
Has identifier KSL-91-15  +
Has publishing details 1991  +
Has title An Approximate Nonmyopic Computation for Value of Information  +
Has where published KSL-91-15  +
Has year 1991  +
Institution Knowledge Systems, AI Laboratory  +
Ksl tr id KSL-91-15  +
Number KSL-91-15  +
Process note YES  +
Title An Approximate Nonmyopic Computation for Value of Information  +
Year 1991  +
Retrieved from "http://tw.rpi.edu/wiki/An_Approximate_Nonmyopic_Computation_for_Value_of_Information"
Personal tools