
TL;DR
This paper explores alternative belief measures beyond traditional probabilities, proposing minimal assumptions and investigating ranking and cumulative measures to better model belief dynamics and knowledge representation.
Contribution
It introduces a minimal set of assumptions for quasi-probabilistic measures and investigates ranking and cumulative measures as novel approaches for belief modeling.
Findings
Ranking measures generalize existing belief measures
Cumulative measures integrate probabilistic and ranking approaches
Proposes frameworks less affected by traditional probability limitations
Abstract
Probability measures by themselves, are known to be inappropriate for modeling the dynamics of plain belief and their excessively strong measurability constraints make them unsuitable for some representational tasks, e.g. in the context of firstorder knowledge. In this paper, we are therefore going to look for possible alternatives and extensions. We begin by delimiting the general area of interest, proposing a minimal list of assumptions to be satisfied by any reasonable quasi-probabilistic valuation concept. Within this framework, we investigate two particularly interesting kinds of quasi-measures which are not or much less affected by the traditional problems. * Ranking measures, which generalize Spohn-type and possibility measures. * Cumulative measures, which combine the probabilistic and the ranking philosophy, allowing thereby a fine-grained account of static and dynamic belief.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsBayesian Modeling and Causal Inference · Logic, Reasoning, and Knowledge · Epistemology, Ethics, and Metaphysics
