Alphabeta Math
LemmaStatement: Literature-sourcedProof: AI-adaptedPipeline-generatedjudge pass (gpt-6-luna)
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.

A bounded likelihood ratio controls KL and log-square moments by Hellinger distance

Statement

Let p,q be probability densities relative to one measure μ, assume p dμ≪q dμ, let h2:=∫(p−q)2dμ, and suppose R:=ess,sup⁡q dμ(p/q)<∞, with p/q=0 on {q=0,p=0}. Then p≪q and for a universal constant C, KL(p dμ∥q dμ)≤Ch2(1+log⁡+R),∫p[log⁡(p/q)]2dμ≤Ch2(1+log⁡+R)2. The logarithm is assigned value zero on {p=0}; the moment integrand is also set to zero there.

Facts & Assumptions

Given: Two probability densities p,q relative to one measure, p dμ≪q dμ, and finite R as in the Statement.

[A1]

Assume AC for the library directional KL convention. The Axiom of Choice Kullback–Leibler divergence

[F1]

Root-L2 Hellinger distance between density laws: h2=∫(p−q)2dμ.

[F2]

Kullback–Leibler divergence: when p dμ≪q dμ, the directional KL divergence is the integral of log⁡(p/q) against p dμ.

Proof

Given: The hypotheses in the Statement.

1.1A1F3givenalgebra

Put u=p/q on {q>0}. The absolute-continuity premise gives p=0 μ-almost everywhere on {q=0}. Define g(u)=(u−1)2 and a(u)=(ulog⁡u−u+1)/g(u), b(u)=u(log⁡u)2/g(u) for u≠1, with their limiting values at u=1 and u=0. At zero, set s=1/u; for s≥1, [F3] gives 0≤log⁡s≤∫1st−3/4dt≤4s1/4. Hence ulog⁡u=−(log⁡s)/s→0 and u(log⁡u)2=(log⁡s)2/s≤16s−1/2→0, so a(0)=1 and b(0)=0. At one, log⁡u/(u−1)→1 by [F3], g(u)/(u−1)2=1/(u+1)2→1/4, and u(log⁡u)2/(u−1)2→1. Also ulog⁡u−u+1=∫1ulog⁡t dt, so [ulog⁡u−u+1]/(u−1)2→1/2; therefore a(1)=2 and b(1)=4. Thus a,b are continuous on [0,2] and bounded there.

2.1F3step 1.1algebra

For u≥2, g(u)=u(1−u−1/2)2≥u(1−2−1/2)2, while 0≤ulog⁡u−u+1≤ulog⁡u and u(log⁡u)2 retain their displayed forms. Hence a(u)≤Clog⁡u and b(u)≤C(log⁡u)2 for a universal C. Combining with step 1.1, for every 0≤u≤R, ulog⁡u−u+1≤Cg(u)(1+log⁡+R),u(log⁡u)2≤Cg(u)(1+log⁡+R)2.

3.1A1F1F2step 2.1algebra∎

Integrating the first inequality in step 2.1 against q dμ gives the KL bound, since ∫q(ulog⁡u−u+1)dμ=∫plog⁡(p/q)dμ by ∫p=∫q=1 and [F2]. Integrating the second gives the log-square bound. Finally ∫qg dμ=h2 by [F1], so both right sides have the claimed factors of h2.

Depends on

Used by

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