We apply the principle of maximum entropy to select a unique joint probability distribution from the set of all joint probability distributions specified by a credal network. In detail, we start by showing that the unique joint distribution of a Bayesian tree coincides with the maximum entropy model of its conditional distributions. This result, however, does not hold anymore for general Bayesian networks. We thus present a new kind of maximum entropy models, which are computed sequentially. We then show that for all general Bayesian networks, the sequential maximum entropy model coincides with the unique joint distribution. Moreover, we apply the new principle of sequential maximum entropy to interval Bayesian networks and more generally to credal networks. We especially show that this application is equivalent to a number of small local entropy maximizations. 1
|
4387
|
Probabilistic Reasoning in Intelligent Systems
– Pearl
- 1988
|
|
2739
|
A mathematical theory of communication
– Shannon
- 1948
|
|
361
|
Statistical Reasoning with Imprecise Probabilities
– Walley
- 1991
|
|
279
|
Information theory and statistical mechanics
– Jaynes
- 1957
|
|
205
|
Probabilistic horn abduction and bayesian networks
– Poole
- 1993
|
|
145
|
Logical Foundations of Probability
– Carnap
- 1950
|
|
131
|
Axiomatic derivation of the principle of maximum entropy and the principle of maximum cross-entropys
– Shore, Johnson
- 1980
|
|
90
|
From statistical knowledge bases to degrees of belief
– Bacchus, Grove, et al.
- 1996
|
|
60
|
Anytime deduction for probabilistic logic
– FRISCH, HADDAWY
- 1994
|
|
57
|
Bayesian and Non-Bayesian Evidential Updating
– Kyburg
- 1987
|
|
49
|
Generating bayesian networks from probability logic knowledge bases
– Haddawy
- 1994
|
|
43
|
A note on the inevitability of maximum entropy
– Paris, Vencovska
- 1990
|
|
42
|
Random Worlds and Maximum Entropy
– Grove, Halpern, et al.
- 1994
|
|
40
|
A method of computing generalized Bayesian probability values for expert systems
– Cheeseman
- 1983
|
|
40
|
Probabilistic deduction with conditional constraints over basic events
– Lukasiewicz
- 1999
|
|
34
|
Local probabilistic deduction from taxonomic and probabilistic knowledge-bases over conjunctive events
– Lukasiewicz
- 1999
|
|
28
|
de Finetti Theory of Probability
– unknown authors
- 1974
|
|
27
|
Interval probability propagation
– Tessem
- 1992
|
|
25
|
Probabilistic default reasoning with conditional constraints
– LUKASIEWICZ
- 2000
|
|
22
|
2U: an exact interval propagation algorithm for polytrees with binary variables
– Fagiuoli, Zaffalon
- 1998
|
|
20
|
Robustness Analysis of Bayesian Networks with Local Convex Sets of Distributions
– Cozman
- 1997
|
|
20
|
Causality and maximum entropy updating
– Hunter
- 1989
|
|
19
|
Decision making with interval influence diagrams
– Breese, Fertig
- 1991
|
|
19
|
Convex sets of probabilities propagation by simulated annealing
– Cano, Cano, et al.
- 1994
|
|
15
|
A genetic algorithm to approximate convex sets of probabilities
– Cano, Moral
- 1996
|
|
14
|
Probabilistic logic programming under maximum entropy
– Lukasiewicz, Kern-Isberner
- 1999
|
|
11
|
Characterizing the principle of minimum cross-entropy within a conditional-logical framework
– Kern-Isberner
- 1998
|
|
9
|
Comments on and corrections to "Axiomatic derivation of the principle of maximum entropy and the principle of minimum cross-entropy
– Johnson, Shore
- 1983
|
|
9
|
In defense of the maximum entropy inference process
– Paris, Vencovska
- 1997
|
|
9
|
Coherent knowledge processing at maximum entropy by SPIRIT
– Rodder, Meyer
- 1996
|
|
7
|
Irrelevance and independence axioms in quasi-Bayesian theory
– Cozman
- 1999
|
|
7
|
Reasoning with probabilities and maximum entropy: The system PIT and its application in LEXMED
– Schramm, Ertel
- 1999
|
|
6
|
Irrelevance and independence relations in Quasi-Bayesian networks
– Cozman
- 1998
|
|
5
|
Irrelevance and conditioning in first-order probabilistic logic
– Koller, Halpern
- 1996
|
|
4
|
A logically sound method for uncertain reasoning with quantified conditionals
– Kern-Isberner
- 1997
|
|
2
|
Combining data and knowledge by maxent-optimisation of probability distributions
– Ertel, Schramm
- 1999
|
|
2
|
Increased robustness of Bayesian networks through probability intervals
– Thone, Guntzer, et al.
- 1997
|
|
