论文信息 - Measure Selection: Notions of Rationality and Representation Independence

Measure Selection: Notions of Rationality and Representation Independence

We take another look at the general problem of selecting a preferred probability measure among those that comply with some given constraints. The dominant role that entropy maximization has obtained in this context is questioned by arguing that the minimum information principle on which it is based could be supplanted by an at least as plausible "likelihood of evidence" principle. We then review a method for turning given selection functions into representation independent variants, and discuss the tradeoffs involved in this transformation.

Manfred Jaeger

[1] Joseph Y. Halpern,et al. Representation Dependence in Probabilistic Inference , 1995, IJCAI.

[2] Marek J. Druzdzel,et al. Elicitation of Probabilities for Belief Networks: Combining Qualitative and Quantitative Information , 1995, UAI.

[3] Manfred Jaeger,et al. Representation Independence of Nonmonotonic Inference Relations , 1996, KR.

[4] Jeff B. Paris,et al. In defense of the maximum entropy inference process , 1997, Int. J. Approx. Reason..

[5] J. Paris. The Uncertain Reasoner's Companion: A Mathematical Perspective , 1994 .

[6] Rodney W. Johnson,et al. Axiomatic derivation of the principle of maximum entropy and the principle of minimum cross-entropy , 1980, IEEE Trans. Inf. Theory.

[7] Manfred Jaeger,et al. Default reasoning about probabilities , 1995 .

[8] Joseph Y. Halpern,et al. Probability Update: Conditioning vs. Cross-Entropy , 1997, UAI.

[9] Jeff B. Paris,et al. A note on the inevitability of maximum entropy , 1990, Int. J. Approx. Reason..

[10] Jos Uffink,et al. The constraint rule of the maximum entropy principle , 1996 .