Representation Dependence in Probabilistic Inference
Representation Dependence in Probabilistic Inference
复制标题
概率推理中的表示依赖性
DOI：
--
复制
发表时间：
1995
期刊：
影响因子：
--
通讯作者：
D. Koller
中科院分区：
文献类型：
--
作者：
Joseph Y. Halpern;D. Koller
非演绎推理系统通常依赖于表示：用两种不同的方式表示相同的情况可能会导致这样的系统返回两个不同的答案。一些人认为这是一个严重的问题。例如，最大熵原理由于其表示依赖性而受到许多批评。然而，几乎没有研究表征依赖的工作。在本文中，我们形式化了这一概念，并证明了它不是最大熵特有的问题。事实上，我们表明，任何表征无关的概率推理过程，忽略不相关的信息本质上是蕴涵，在一个精确的意义上。此外，我们还证明了表示独立性甚至与弱默认独立性假设不相容。然后，我们证明了在一类受限的表示变化下的不变性可以在表示独立性和其他期望之间形成一个合理的妥协，并提供了一个使用相对熵提供这种受限表示独立性的推理过程族的构造。
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.