Iterated Belief Change, Computationally
Kai Sauerwald, Christoph Beierle
TL;DR
This paper explores the computational complexity of iterated belief change, demonstrating that belief revision processes can simulate any Turing machine, thus establishing their Turing completeness even under standard principles.
Contribution
It proves that iterated belief revision is Turing complete, linking belief dynamics to computational universality under common revision principles.
Findings
Iterated belief revision is Turing complete.
Belief change processes can simulate any computation.
Standard principles like Darwiche-Pearl do not limit computational power.
Abstract
Iterated Belief Change is the research area that investigates principles for the dynamics of beliefs over (possibly unlimited) many subsequent belief changes. In this paper, we demonstrate how iterated belief change is connected to computation. In particular, we show that iterative belief revision is Turing complete, even under the condition that broadly accepted principles like the Darwiche-Pearl postulates for iterated revision hold.
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
TopicsLogic, Reasoning, and Knowledge · Machine Learning and Algorithms · Bayesian Modeling and Causal Inference