Finding Most Probable Worlds of Probabilistic Logic Programs

Authors:
Samir Khuller;Vanina Martinez;Dana Nau;Gerardo Simari;Amy Sliva;V. S. Subrahmanian
Affiliations:
University of Maryland College Park, College Park, MD 20742, USA;University of Maryland College Park, College Park, MD 20742, USA;University of Maryland College Park, College Park, MD 20742, USA;University of Maryland College Park, College Park, MD 20742, USA;University of Maryland College Park, College Park, MD 20742, USA;University of Maryland College Park, College Park, MD 20742, USA
Venue:
SUM '07 Proceedings of the 1st international conference on Scalable Uncertainty Management
Year:
2007

Citing 9
Cited 4

Probabilistic logic

Artificial Intelligence
Quantitative deduction and its fixpoint theory

Journal of Logic Programming
Foundations of logic programming; (2nd extended ed.)

Foundations of logic programming; (2nd extended ed.)
A logic for reasoning about probabilities

Information and Computation - Selections from 1988 IEEE symposium on logic in computer science
Probabilistic logic programming

Information and Computation
A Parametric Approach to Deductive Databases with Uncertainty

IEEE Transactions on Knowledge and Data Engineering
Probabilistic Logic Programming and Bayesian Networks

ACSC '95 Proceedings of the 1995 Asian Computing Science Conference on Algorithms, Concurrency and Knowledge
Probalilistic Logic Programming under Maximum Entropy

ECSQARU '95 Proceedings of the European Conference on Symbolic and Quantitative Approaches to Reasoning and Uncertainty
CARA: A Cultural-Reasoning Architecture

IEEE Intelligent Systems

Scaling Most Probable World Computations in Probabilistic Logic Programs

SUM '08 Proceedings of the 2nd international conference on Scalable Uncertainty Management
Forecasting complex group behavior via multiple plan recognition

Frontiers of Computer Science in China
Terrorist organization behavior prediction algorithm based on context subspace

ADMA'11 Proceedings of the 7th international conference on Advanced Data Mining and Applications - Volume Part II
Focused most probable world computations in probabilistic logic programs

Annals of Mathematics and Artificial Intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

Probabilistic logic programs have primarily studied the problem of entailment of probabilistic atoms. However, there are some interesting applications where we are interested in finding a possible world that is most probable. Our first result shows that the problem of computing such "maximally probable worlds" (MPW) is intractable. We subsequently show that we can often greatly reduce the size of the linear program used in past work (by Ng and Subrahmanian) and yet solve the problem exactly. However, the intractability results still make computational efficiency quite impossible. We therefore also develop several heuristics to solve the MPW problem and report extensive experimental results on the accuracy and efficiency of such heuristics.