arXivDaily arXiv每日学术速递 周一至周五更新
arXiv cs/0312048cs.AIcs.LO
收藏

概率推理中的表征依赖

Representation Dependence in Probabilistic Inference

Joseph Y. Halpern, Daphne Koller

摘要:

非演绎推理系统通常是{ \em表示依赖}的:以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。有些人认为这是一个严重的问题。例如,最大熵原理由于其表征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,我们正式这个概念,并表明这不是一个特定的最大熵的问题。事实上,我们表明,任何表示独立的概率推理过程,忽略不相关的信息,本质上是蕴涵,在一个精确的意义。此外,我们表明,代表独立性是不兼容的,即使是一个弱的默认假设的独立性。然后,我们表明,在一个有限的类的表示变化的不变性可以形成一个合理的妥协之间的表示独立性和其他desiderata,并提供了一个家庭的推理程序,提供这种限制表示独立性,使用相对熵的建设。

英文摘要:

Non-deductive reasoning systems are often {\em 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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑