Abstract:
A rule-based program will return a set of answers to each query. An impure program, which includes the Prolog cut "! " and "not(\Delta) " operators, can return different answers if its rules are re-ordered. There are also many reasoning systems that return only the first answer found for each query; these first answers, too, depend on the rule order, even in pure rule-based systems. A theory revision algorithm, seeking a revised rule-base whose expected accuracy, over the distribution of queries, is optimal, should therefore consider modifying the order of the rules. This paper first shows that a polynomial number of training "labeled queries " (each a query paired with its correct answer) provides the distribution information necessary to identify the optimal ordering. It then proves, however, that the task of determining which ordering is optimal, once given this distributional information, is intractable even in trivial situations; e.g., even if each query is an atomic literal, we are seeking only a "perfect " theory, and the rule base is propositional. We also prove that this task is not even approximable: Unless P = NP, no polynomial time algorithm can produce an ordering of an n-rule theory whose accuracy is within n fl of optimal, for some fl? 0. We next prove similar hardness, and non-approximatability, results for the related tasks of determining, in these impure contexts, (1) the optimal ordering of the antecedents; (2) the optimal set of new rules to add; and (3) the optimal set of existing rules to delete.
Citations
|
7715
|
Computers and Intractability: A Guide to the Theory of NP-Completeness
– Garey, Johnson
- 1979
|
|
843
|
Efficient induction of logic programs
– Muggleton, Feng
- 1990
|
|
637
|
Estinwtion of Dependences Based on Empirical Data
– Vapnik
- 1982
|
|
515
|
Proof verification and hardness of approximation problems
– Arora, Lund, et al.
- 1992
|
|
448
|
Knowledge In Flux: modeling the dynamics of epistemic states
– Gardenfors
- 1988
|
|
434
|
On the logic of theory change: partial meet contraction and revision functions
– GÄRDENFORS
- 1985
|
|
427
|
A measure of asymptotic efficiency for tests of a hypothesis based on the sum of observations
– Chernoff
- 1995
|
|
304
|
On the difference between updating a knowledge base and revising it, in P. Gärdenfors ed.: Belief Revision
– KATSUNO
- 1992
|
|
210
|
Solving TimeDependent Planning Problems
– Boddy, Dean
- 1989
|
|
184
|
Investigations into a theory of knowledge base revision: Preliminary Report
– Dalal
- 1988
|
|
166
|
Preferred subtheories: an extended logical framework for default reasoning
– Brewka
- 1989
|
|
130
|
On the complexity of propositional knowledge base revision, updates and counterfactuals
– Eiter, Gottlob
- 1992
|
|
124
|
On the logic of iterated belief revision
– Darwiche, Pearl
- 1997
|
|
120
|
Foundations of a functional approach to knowledge representation
– Levesque
- 1984
|
|
116
|
Theory refinement combining analytical and empirical methods
– Ourston, Mooney
- 1994
|
|
110
|
Two Theses of Knowledge Representation: Language Restrictions, Taxonomic Classification, and The Utility of Representation Services
– Doyle, Patil
- 1991
|
|
79
|
Structure in approximation classes
– Crescenzi, Kann, et al.
- 1999
|
|
77
|
Linear time algorithms for testing the satisfiability of propositional horn formulae
– Dowling, Gallier
- 1984
|
|
71
|
PAC-learnability of determinate logic programs
– Dzeroski, Muggleton, et al.
- 1992
|
|
61
|
On the Approximability of NP-Complete Optimization Problems
– Kann
- 1992
|
|
57
|
Revision sequences and nested conditionals
– Boutilier
- 1993
|
|
48
|
Belief revision: a critique
– Friedman, Halpern
- 1996
|
|
41
|
Machine learning
– Dietterich
- 1990
|
|
37
|
Machine invention of first order predicates by inverting resolution
– Muggleton, Buntine
- 1988
|
|
34
|
Finding the optimal derivation strategy in a redundant knowledge base
– Greiner
- 1991
|
|
33
|
Pac-learning recursive logic programs: efficient algorithms
– Cohen
- 1995
|
|
28
|
Pac-learning recursive logic programs: negative results
– Cohen
- 1995
|
|
28
|
Belief revision and rational inference
– Freund, Lehmann
- 1994
|
|
28
|
Generalizing prioritization
– Grosof
- 1991
|
|
28
|
Universal subgoaling and chunking: The automatic generation and learning of goal hierarchies
– Laird, Rosenbloom, et al.
- 1986
|
|
27
|
A methodology for evaluating theory revision systems
– Wogulis, Pazzani
- 1993
|
|
24
|
Incremental recompilation of knowledge
– Gogic, Papadimitriou, et al.
- 1994
|
|
15
|
Pac-learning non-recursive Prolog clauses
– Cohen
- 1995
|
|
15
|
The complexity of theory revision
– Greiner
- 1995
|
|
11
|
Theory revision in fault hierarchies
– Langley, Drastal, et al.
- 1994
|
|
9
|
The difficulties of learning logic programs with cut
– Bergadano, Gunetti
- 1993
|
|
8
|
The Automated Analysis of Rule-based Systems Based on their Procedural Semantics
– Evertsz
- 1991
|
|
5
|
A Practical guide to knowledge acquisition. Addison-Wesley Pub Co
– Scott, Clayton, et al.
- 1991
|
|
4
|
Toward efficient agnostic leaning
– Kearns, Schapire, et al.
- 1992
|
|
4
|
The refinement of probabilistic rule sets: sociopathic interactions
– Wilkins, Ma
- 1994
|
|
2
|
Some results on the computational complexity of refining certainty factors
– Ling, Valtorta
- 1991
|
|
2
|
Refinement of uncertain rule bases via reduction
– Ling, Valtorta
- 1995
|
|
1
|
PAC-learnability of determiniate logic programs
– Dzeroski, Muggleton, et al.
- 1992
|
|
