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.
Root-L2 Hellinger distance between density laws
Definition
Let be a measure space and let be measurable densities with . They define probability laws and (Probability measures and probability spaces). Their root-L2 Hellinger distance, with the root-L2 normalization, is
The dominating measure is fixed throughout a use of this definition. Changing either density on a -null set does not change the value, since the integrand changes only on a null set. This definition does not assert that separate choices of density versions are jointly measurable in an additional parameter.
Remarks
The integrand is measurable: square root is Borel on , and subtraction and squaring preserve measurability (Composition with a Borel measurable outer map preserves measurability, Arithmetic and lattice operations preserve measurability whenever they are defined). For , . Thus pointwise; monotonicity and additivity of the nonnegative integral (Monotonicity and nonnegative homogeneity of the nonnegative integral, Additivity of the nonnegative Lebesgue integral) give , so the defining integral is finite. The set functions and are measures by The measure with density relative to , and their total masses are one, so they are probability laws by Probability measures and probability spaces. Changing either density on a -null set changes the integrand only on a null set, whose nonnegative integral vanishes (A nonnegative integral over a null set vanishes), confirming the stated version invariance.
Depends on
- Probability measures and probability spaces
- The measure with density $f$ relative to $\mu$
- Arithmetic and lattice operations preserve measurability whenever they are defined
- Composition with a Borel measurable outer map preserves measurability
- Additivity of the nonnegative Lebesgue integral
- Monotonicity and nonnegative homogeneity of the nonnegative integral
- A nonnegative integral over a null set vanishes
Used by
- Small L² log-density perturbations can remain far in Hellinger distance Example
- A bounded likelihood ratio controls KL and log-square moments by Hellinger distance Lemma
- Countably partitioned sieves yield posterior contraction by weighted entropy Lemma
- Hellinger distance is a metric and controls L1 and total variation Lemma
- Hellinger entropy for compact-location normal mixtures in a scale band Lemma
- Sieve metric entropy produces uniform exponential tests Lemma
- Supremum distance controls local log-Gaussian density distances Lemma
- The mixture prior places local KL and log-square mass near a compact smooth truth Lemma
- Dirichlet normal-mixture posterior contraction Theorem
- IID posterior contraction by entropy and prior mass Theorem
Dependency tree · two levels
29 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
- Ghosal, Ghosh and van der Vaart, Convergence rates of posterior distributions, §2 (standard reference, not scraped)
- Ghosal, The Dirichlet Process, Related Priors and Posterior Asymptotics, §2.5 (standard reference, not scraped)
- Kleijn, Bayesian Statistics for Frequentists, §6.4 (standard reference, not scraped)