Probalilistic Logic Programming under Maximum Entropy

@inproceedings{Lukasiewicz1999ProbalilisticLP,
  title={Probalilistic Logic Programming under Maximum Entropy},
  author={Thomas Lukasiewicz and Gabriele Kern-Isberner},
  booktitle={ESCQARU},
  year={1999}
}
In this paper, we focus on the combination of probabilistic logic programming with the principle of maximum entropy. We start by defining probabilistic queries to probabilistic logic programs and their answer substitutions under maximum entropy. We then present an efficient linear programming characterization for the problem of deciding whether a probabilistic logic program is satisfiable. Finally, and as a central contribution of this paper, we introduce an efficient technique for… 

Probabilistic logic programming with conditional constraints

TLDR
It is shown that probabilistic logic programming under certain syntactic and semantic restrictions is closely related to van Emden's quantitative deduction, and thus has computational properties similar to calssical logic programming.

Probabilistic Logic Programming with Conditional Constraints Probabilistic Logic Programming with Conditional Constraints Revised Version, May 2000

TLDR
It is shown that probabilistic logic programming under certain syntactic and semantic restrictions is close ly related to van Emden’s quantitative deduction, and thus has computational properties similar to c lassical logic programming.

Finding Most Probable Worlds of Probabilistic Logic Programs

TLDR
The first result shows that the problem of computing "maximally probable worlds" (MPW) is intractable, and it is subsequently shown that one can often greatly reduce the size of the linear program used in past work and yet solve the problem exactly.

Using Histograms to Better Answer Queries to Probabilistic Logic Programs

TLDR
This paper provides a new method to answer probabilistic queries that tries to come up with a histogram that "maps" the probability that the objective function will have a value in a given interval, subject to a set of linear constraints.

Credal Networks under Maximum Entropy

TLDR
This work presents a new kind of maximum entropy models, which are computed sequentially and show that for all general Bayesian networks, the sequential maximum entropy model coincides with the unique joint distribution.

Focused most probable world computations in probabilistic logic programs

TLDR
It is shown that one can significantly reduce the number of worlds to be considered by defining a “reduced” linear program whose solution is in one-one correspondence with the exact solution to the MPW problem.

Maximising Entropy Efficiently

TLDR
The proposed simplification of the entropy maximisation task may be exploited to construct a proof theory for probabilistic logic.

Scaling Most Probable World Computations in Probabilistic Logic Programs

TLDR
It is shown that one can significantly reduce the number of worlds to be considered by defining a "reduced" linear program whose solution is in one-one correspondence with the exact solution to the MPW problem.

Probabilistic Logic Programming under Inheritance with Overriding

TLDR
This work presents probabilistic logic programming with overriding based on new notions of entailment for reasoning with conditional constraints, which are obtained from the classical notion of logical entailment by adding inheritance with overriding.

References

SHOWING 1-10 OF 29 REFERENCES

Probabilistic Logic Programming

TLDR
It is shown that deduction in the defined probabilistic logic pro grams is computationally more complex than deduction in classical logic programs, and a linear programming approach to deduction in probabilist logic programs is elaborate, which is efficient in interesting specia l cases.

Probabilistic Deduction with Conditional Constraints over Basic Events

TLDR
It is shown that globally complete probabilistic deduction with conditional constraints over basic events is NP-hard, and it is shown how these nonlinear programs can be transformed into equivalent linear programs, which are solvable in polynomial time in the size of the conditional constraint trees.

Characterizing the Principle of Minimum Cross-Entropy Within a Conditional-Logical Framework

Probabilistic Logic

  • N. Nilsson
  • Philosophy, Computer Science
    Artif. Intell.
  • 1986

Hybrid Probabilistic Programs

Generating Bayesian Networks from Probablity Logic Knowledge Bases

Random worlds and maximum entropy

TLDR
It is shown that when the vocabulary underlying phi and theta uses constants and unary predicates only, one can in many cases use a maximum entropy computation to compute the degree of belief.

Logic Programming

  • K. Apt
  • Computer Science
    Handbook of Theoretical Computer Science, Volume B: Formal Models and Sematics
  • 1990