Probabilistic reasoning in intelligent systems: networks of plausible inference
Probabilistic reasoning in intelligent systems: networks of plausible inference
A note on the inevitability of maximum entropy
International Journal of Approximate Reasoning
Nonmonotonic reasoning, preferential models and cumulative logics
Artificial Intelligence
Representing and reasoning with probabilistic knowledge: a logical approach to probabilities
Representing and reasoning with probabilistic knowledge: a logical approach to probabilities
What does a conditional knowledge base entail?
Artificial Intelligence
Elements of information theory
Elements of information theory
Artificial Intelligence
The uncertain reasoner's companion: a mathematical perspective
The uncertain reasoner's companion: a mathematical perspective
From statistical knowledge bases to degrees of belief
Artificial Intelligence
A Maximum Entropy Approach to Nonmonotonic Reasoning
IEEE Transactions on Pattern Analysis and Machine Intelligence
A semantic theory of abstractions
IJCAI'95 Proceedings of the 14th international joint conference on Artificial intelligence - Volume 1
Representation dependence in probabilistic inference
IJCAI'95 Proceedings of the 14th international joint conference on Artificial intelligence - Volume 2
Inductive reasoning and chance discovery
Minds and Machines - Machine learning as experimental philosophy of science
Hi-index | 0.00 |
Non-deductive reasoning systems are often representation dependent: representing the same situation in two different ways may cause such a system to return two different answers. Some have viewed this as a significant problem. For example, the principle of maximum entropy has been subjected to much criticism due to its representation dependence. There has, however, been almost no work investigating representation dependence. In this paper, we formalize this notion and show that it is not a problem specific to maximum entropy. In fact, we show that any representation-independent probabilistic inference procedure that ignores irrelevant information is essentially entailment, in a precise sense. Moreover, we show that representation independence is incompatible with even a weak default assumption of independence. We then show that invariance under a restricted class of representation changes can form a reasonable compromise between representation independence and other desiderata, and provide a construction of a family of inference procedures that provides such restricted representation independence, using relative entropy.