Statistical Foundations for Default Reasoning

We describe a new approach to default reasoning, based on a principle of indi erence among possible worlds. We interpret default rules as extreme statistical statements, thus obtaining a knowledge base KB comprised of statistical and rst-order statements. We then assign equal probability to all worlds consistent with KB in order to assign a degree of belief to a statement '. The degree of belief can be used to decide whether to defeasibly conclude '. Various natural patterns of reasoning, such as a preference for more speci c defaults, indi erence to irrelevant information, and the ability to combine independent pieces of evidence, turn out to follow naturally from this technique. Furthermore, our approach is not restricted to default reasoning it supports a spectrum of reasoning, from quantitative to qualitative. It is also related to other systems for default reasoning. In particular, we show that the work of Goldszmidt et al., 1990], which applies maximum entropy ideas to...

• Type: Conference
• Year: 1993
• Where: IJCAI
• Authors: Fahiem Bacchus, Adam J. Grove, Joseph Y. Halpern, Daphne Koller
• Keywords: Default Reasoning, Extreme Statistical Statements, IJCAI 1993, IJCAI 2007, Indi Erence