Representation Theorems for Strong Predicate Exchangeability in Pure Inductive Logic
Malte S. Klie{\ss}

TL;DR
This paper establishes a de Finetti-style representation theorem for probability functions in Pure Inductive Logic that satisfy Strong Predicate Exchangeability and Unary Language Invariance, advancing the theoretical understanding of symmetry principles.
Contribution
It introduces a new representation theorem for probability functions under Strong Predicate Exchangeability, bridging the gap between Predicate and Atom Exchangeability.
Findings
Proves a de Finetti-style representation theorem for these probability functions.
Shows the relationship between Strong Predicate Exchangeability and Unary Language Invariance.
Provides a formal foundation for symmetry principles in Pure Inductive Logic.
Abstract
In Pure Inductive Logic, the principle of Strong Predicate Exchangeability is a rational principle based on symmetry that sits in between the principles of Predicate Exchangeability and Atom Exchangeability. We will show a de Finetti - style representation theorem for probability functions that satisfy this principle in addition to Unary Language Invariance.
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
TopicsMathematical and Theoretical Analysis · Computability, Logic, AI Algorithms · Logic, Reasoning, and Knowledge
