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 finite label has a conditional probability function
Statement
Assume AC. Let a supervised prediction problem have a measurable instance space , finite label set with distinct labels, the full power-set sigma-algebra on , and , and joint probability law on ; let and be its coordinate random variables and let , the sigma-algebra generated by . There is a measurable function , where has its subspace Borel sigma-algebra, such that for every label index and ,
Statement references
Supervised prediction problems: supplies measurable instance and label spaces, the joint law, and the coordinate random variables; here the finite label sigma-algebra is explicitly the full power set.
Conditional expectation given a sigma algebra: a conditional-expectation version is measurable with respect to the conditioning sigma-algebra and has the same integrals on its events.
Conditional expectation exists by radon nikodym: under AC, an integrable real random variable has a conditional-expectation version given any sub-sigma-algebra.
Durrett, Section 4.1: defines conditional expectation by event integrals and constructs it from Radon–Nikodym derivatives.
Facts & Assumptions
Given: AC; a finite-label supervised prediction problem with joint law and full power-set label sigma-algebra; the instance coordinate ; and the sub-sigma-algebra .
Assume AC, the choice principle used by the published conditional-expectation existence theorem. The Axiom of Choice
Each indicator is integrable because it is bounded by on a probability space; under AC, its conditional-expectation version exists and has the defining event integrals. Probability measures and probability spaces Conditional expectation given a sigma algebra Conditional expectation exists by radon nikodym
Conditional expectation preserves order and constants almost surely. Basic algebra and order properties of conditional expectation
A conditional-expectation version is unique almost surely. Conditional expectation is unique almost surely
Integrable functions equal almost surely have identical integrals over every measurable event. Two integrable functions are equal almost everywhere exactly when all of their indefinite integrals agree
Measurability is determined by preimages of measurable sets. A measurable function between measurable spaces
The family of all inverse images is a sigma-algebra because inverse images preserve complements and countable unions; by definition it is .
Finite sums, products by indicators, and level sets of measurable real functions are measurable. Closure properties of measurable functions used by the integral A measurable function between measurable spaces
Proof
For each , choose a version of , which exists by [A1,F1]. Order preservation and preservation of constants give almost surely by [F2]. Set and define to equal on and on . Since both pieces are -measurable, is -measurable; it takes values in everywhere and equals almost surely. By [F3], it has the same event integrals, so it remains a conditional-expectation version. Linearity shows that is a version of the conditional expectation of ; the constant 1 is another version, so [F6] gives almost surely. Hence almost surely.
For each label and rational , the event equals for some by [F5]. AC permits choosing these sets for the countable family of label-rational pairs. Define . For , ; for this sublevel set is empty and for it is all of . Thus each is measurable and takes values in by [F4,F7].
For every and , the rationals satisfying are exactly those with . Their infimum is when this value is below ; at value the rational set is empty and the filler gives the same value. Thus everywhere. The measurable set is well-defined by [F7]. Define on and off . Its coordinates are measurable. The inverse image of an open rational box in is a finite intersection of coordinate preimages, and these boxes form a countable basis, so is Borel measurable into and hence measurable into the subspace . It takes values in everywhere, and almost surely because almost surely.
For every and label index , the event belongs to . The conditional-expectation identity [F1] and almost-sure equality [F3] therefore give This is the claimed event identity for every class.
Depends on
- Supervised prediction problems
- Probability measures and probability spaces
- Conditional expectation given a sigma algebra
- Conditional expectation exists by radon nikodym
- The Axiom of Choice
- Basic algebra and order properties of conditional expectation
- Two integrable functions are equal almost everywhere exactly when all of their indefinite integrals agree
- A measurable function between measurable spaces
- Closure properties of measurable functions used by the integral
- Conditional expectation is unique almost surely
Used by
Dependency tree · two levels
31 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
- Rick Durrett, Probability: Theory and Examples, 5th ed., Section 4.1, pp. 205–207 (standard reference, not scraped)