Results 1  10
of
18
Fundamental Concepts of Qualitative Probabilistic Networks
 ARTIFICIAL INTELLIGENCE
, 1990
"... Graphical representations for probabilistic relationships have recently received considerable attention in A1. Qualitative probabilistic networks abstract from the usual numeric representations by encoding only qualitative relationships, which are inequality constraints on the joint probability dist ..."
Abstract

Cited by 119 (6 self)
 Add to MetaCart
Graphical representations for probabilistic relationships have recently received considerable attention in A1. Qualitative probabilistic networks abstract from the usual numeric representations by encoding only qualitative relationships, which are inequality constraints on the joint probability distribution over the variables. Although these constraints are insufficient to determine probabilities uniquely, they are designed to justify the deduction of a class of relative likelihood conclusions that imply useful decisionmaking properties. Two types of qualitative relationship are defined, each a probabilistic form of monotonicity constraint over a group of variables. Qualitative influences describe the direction of the relationship between two variables. Qualitative synergies describe interactions among influences. The probabilistic definitions chosen justify sound and efficient inference procedures based on graphical manipulations of the network. These procedures answer queries about qualitative relationships among variables separated in the network and determine structural properties of optimal assignments to decision variables.
Preferential Semantics for Goals
 In Proceedings of the National Conference on Artificial Intelligence
, 1991
"... Goals, as typically conceived in AI planning, provide an insufficient basis for choice of action, and hence are deficient as the sole expression of an agent's objectives. Decisiontheoretic utilities offer a more adequate basis, yet lack many of the computational advantages of goals. We provide a pr ..."
Abstract

Cited by 114 (19 self)
 Add to MetaCart
Goals, as typically conceived in AI planning, provide an insufficient basis for choice of action, and hence are deficient as the sole expression of an agent's objectives. Decisiontheoretic utilities offer a more adequate basis, yet lack many of the computational advantages of goals. We provide a preferential semantics for goals that grounds them in decision theory and preserves the validity of some, but not all, common goal operations performed in planning. This semantic account provides a criterion for verifying the design of goalbased planning strategies, thus providing a new framework for knowledgelevel analysis of planning systems. Planning to achieve goals In the predominant AI planning paradigm, planners construct plans designed to produce states satisfying particular conditions called goals. Each goal represents a partition of possible states of the world into those satisfying and those not satisfying the goal. Though planners use goals to guide their reasoning, the crude b...
Path Planning under TimeDependent Uncertainty
 In Proceedings of the Eleventh Conference on Uncertainty in Artificial Intelligence
, 1995
"... Standard algorithms for finding the shortest path in a graph require that the cost of a path be additive in edge costs, and typically assume that costs are deterministic. We consider the problem of uncertain edge costs, with potential probabilistic dependencies among the costs. Although these depend ..."
Abstract

Cited by 30 (3 self)
 Add to MetaCart
Standard algorithms for finding the shortest path in a graph require that the cost of a path be additive in edge costs, and typically assume that costs are deterministic. We consider the problem of uncertain edge costs, with potential probabilistic dependencies among the costs. Although these dependencies violate the standard dynamicprogramming decomposition, we identify a weaker stochastic consistency condition that justifies a generalized dynamicprogramming approach based on stochastic dominance. We present a revised pathplanning algorithm and prove that it produces optimal paths under timedependent uncertain costs. We illustrate the algorithm by applying it to a model of stochastic bus networks, and present sample performance results comparing it to some alternatives. For the case where all or some of the uncertainty is resolved during path traversal, we extend the algorithm to produce optimal policies. This report is based on a paper presented at the Eleventh Conference on Unc...
Incremental tradeoff resolution in qualitative probabilistic networks
 Proceedings of the Fourteenth Conference on Uncertainty in Artificial Intelligence
, 1998
"... Qualitative probabilistic reasoning in a Bayesianetwork often reveals tradeoffs: relationships that are ambiguous due to competing qualitative influences. We present two techniques that combine qualitative and numeric probabilistic reasoning to resolve such tradeoffs, inferring the qualitative relat ..."
Abstract

Cited by 9 (3 self)
 Add to MetaCart
Qualitative probabilistic reasoning in a Bayesianetwork often reveals tradeoffs: relationships that are ambiguous due to competing qualitative influences. We present two techniques that combine qualitative and numeric probabilistic reasoning to resolve such tradeoffs, inferring the qualitative relationship between nodes in a Bayesia network. The first approach incrementally marginalizes nodes in network, and the second incrementally refines the state spaces of random variables. Both provide systematic methods for tradeoff resolution at potentially lower computational cost than application of purely numeric methods.
Using StochasticDominance Relationships for Bounding Travel Times in Stochastic Networks
, 1999
"... We consider stochastic networks' in which link travel times are dependent, discrete random variables. We present methods' for computing bounds' on path travel times using stochastic dominance relationships among link travel times, and discuss techniques for controlling tightness of the bounds'. We a ..."
Abstract

Cited by 7 (5 self)
 Add to MetaCart
We consider stochastic networks' in which link travel times are dependent, discrete random variables. We present methods' for computing bounds' on path travel times using stochastic dominance relationships among link travel times, and discuss techniques for controlling tightness of the bounds'. We apply these methods' to shortestpath problems, show that the proposed algorithm can provide bounds' on the recommended path, and elaborate on extensions of the algorithm for demonstrating the anytime property.
How larger demand variability may lead to lower costs in the Newsvendor Problem
, 1996
"... In this paper we consider the Newsvendor Problem. Intuition may lead to the hypothesis that in this stochastic inventory problem a higher demand variability results in larger variances and in higher costs. In a recent paper, Song (1994a) has proved that the intuition is correct for many demand distr ..."
Abstract

Cited by 7 (0 self)
 Add to MetaCart
In this paper we consider the Newsvendor Problem. Intuition may lead to the hypothesis that in this stochastic inventory problem a higher demand variability results in larger variances and in higher costs. In a recent paper, Song (1994a) has proved that the intuition is correct for many demand distributions that are commonly used in practice, such as for the Normal distribution function. However, this paper shows that there exist demand distributions for which the intuition is misleading, i.e., for which larger variances occur in combination with lower costs. To characterize these demand distributions we use stochastic dominance relations. Keywords: Newsvendor problem, demand variability, stochastic dominance. We consider the traditional singleitem singleperiod Newsvendor Problem with continuous product demand. Let the demand D be randomly distributed with distribution function F (\Delta), finite mean ¯ and variance oe 2 . There is an underage cost p and an overage cost h per unit ...
Using Qualitative Relationships for Bounding Probability Distributions
 Proceedings of the 14th Conference on Uncertainty in Artificial Intelligence
, 1998
"... We exploit qualitative probabilistic relationships among variables for computing bounds of conditional probability distributions of interest in Bayesian networks. Using the signs of qualitative relationships, we can implement abstraction operations that are guaranteed to bound the distributions ..."
Abstract

Cited by 6 (3 self)
 Add to MetaCart
We exploit qualitative probabilistic relationships among variables for computing bounds of conditional probability distributions of interest in Bayesian networks. Using the signs of qualitative relationships, we can implement abstraction operations that are guaranteed to bound the distributions of interest in the desired direction. By evaluating incrementally improved approximate networks, our algorithm obtains monotonically tightening bounds that converge to exact distributions. For supermodular utility functions, the tightening bounds monotonically reduce the set of admissible decision alternatives as well. 1 Introduction Approximation techniques have gained increasing interest among those employing Bayesian networks for probabilistic reasoning, despite the fact that computing a desired probability distribution to a fixed degree of accuracy has been shown to be NPhard (Dagum & Luby 1993). Approximation techniques offer reasonable prospects of significant accuracy, and ...
Lower Partial Moments As Measures of Perceived Risk  An Experimental Study
, 1998
"... The paper reports the results of an experiment on individual investors’ risk perception in a stock market context under two different modes of information presentation (framings). While the concentration on two moments of a return distribution has been a cornerstone of neoclassic finance theory fro ..."
Abstract

Cited by 6 (0 self)
 Add to MetaCart
The paper reports the results of an experiment on individual investors’ risk perception in a stock market context under two different modes of information presentation (framings). While the concentration on two moments of a return distribution has been a cornerstone of neoclassic finance theory from the start (Markowitz 1952) an alternative’s mean and variance have been selected more by convenience and ease of computation than by theoretical or empirical justification. Even though the most influential models are based on variance as risk measure there has always been much discontent with this proposal. The symmetrical nature of variance does not capture the common notion of risk as something undesired, e. g. negative deviations from a reference point. Instead, lower partial moments (LPM) seem to be more appropriate for measuring risk. The purpose of this paper is to examine experimentally private investors’ risk perception in a financial context. The focus is on the correspondence of people’s risk perceptions with specific LPMs. The main findings can be summarized as follows. First, symmetrical risk measures like variance can be clearly dismissed in favor of shortfall measures like LPMs. Second, the reference point (target) of individuals for defining losses is not a distribution’s mean but the initial price in a time series of stock prices. Third, the LPM which explains risk perception best is the LPM0, i. e. the probability of loss. Fourth,
Stochastic Dominance: Theory and Applications
, 1996
"... This is a chapter of a book manuscript entitled Topics in Microeconomics . The chapter starts with basic stochastic dominance theorems. These results are useful in a large range of economic applications. Several applications are developed: the theory of labor supply under uncertainty, the theory of ..."
Abstract
 Add to MetaCart
This is a chapter of a book manuscript entitled Topics in Microeconomics . The chapter starts with basic stochastic dominance theorems. These results are useful in a large range of economic applications. Several applications are developed: the theory of labor supply under uncertainty, the theory of the firm under price uncertainty, auction theory, the theory of optimal portfolio selection, oligopoly theory, and the analysis of consistent rankings of income distributions. filename: sdpp.tex 1 "Only risk is sure." William Shakespeare (The Merchant of Venice) 1 Introduction Decision problems under uncertainty concern the choice between random payoffs. For a rational agent with a known utility function, one random variable is preferred if it maximizes expected utility. This is easy enough in theory. However, in practice it is often difficult to find an agent's utility function. Therefore it would be most useful to know whether a random variable is the dominant choice because it is pre...