How statement and proof provenance work
The first chip identifies the source of the statement or construction; the second identifies the source of its local proof or verification.
- Literature-sourced: the exact statement appears in a cited source; only wording and notation differ.
- AI-adapted: a semantically identical restatement of literature-sourced material, modulo indexing, notation, and boundary cases adopted by the library.
- AI-generated: a genuinely novel statement formulated by AI, with no source for the claim itself.
These labels describe origin, not correctness: citations and verification chips remain separate evidence.
KL projection sets and relative KL neighborhoods
Definition
Assume AC as required by the imported directional KL convention Kullback–Leibler divergence. Let be a metric space, where is its Borel sigma-algebra. Let be a sample space with a fixed sigma-finite dominating measure. Suppose the supplied finite-valued densities and are jointly measurable and normalized relative to , and observations are IID from . Use the directional convention for Kullback–Leibler divergence: Assume and The set is the KL projection set of the truth onto the model. The distance to the KL projection set is A relative KL neighborhood of of radius is
For any selected with finite contrast, the relative contrast on satisfies whenever the displayed log ratio is integrable. This definition allows to contain multiple parameters and does not assert that the posterior selects one of them.
Depends on
Used by
- Weak tests against likelihood tilts do not ensure almost-sure posterior consistency Counterexample
- Likelihood-tilted measures at a KL projection Definition
- A finite misspecified model with a unique KL projection Example
- A likelihood tilt can be a finite measure of mass above one Example
- A likelihood tilt can be a finite measure of mass below one Example
- A nonunique KL projection set need not select one parameter Example
- Distant alternatives can prevent uniform testability Example
- Exponential tests and KL mass force posterior exclusion Lemma
- KL-neighborhood prior mass lower-bounds the likelihood denominator Lemma
- Compact models admit tests at a unique KL projection under fractional-moment continuity Proposition
- Posterior consistency at a KL projection Theorem
Dependency tree · two levels
38 results within two dependency steps of this one, each drawn at its shortest distance from it. An arrow runs from a result to what uses it, so the chart reads left to right and ends at this result, which carries a heavier outline. Every node is a link to that result. Click elsewhere on the chart to enlarge it.
Sources
- B. J. K. Kleijn and A. W. van der Vaart, The Bernstein-Von-Mises Theorem under Misspecification, §4.1, pp. 378–379 (standard reference, not scraped)