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.
Latent-variable joint and observed-data factorization
Definition
Let , , and be measurable spaces (sets equipped with sigma-algebras; Measurable spaces and measurable sets). Let and be sigma-finite reference measures on the observation and latent spaces; each has a countable measurable cover by sets of finite measure (Finite, sigma-finite, and semifinite measures). The finite product sigma-algebra is generated by measurable rectangles (The product sigma-algebra and its finite iterates). The product reference measure is the one supplied by For sigma-finite factors, the product measure exists, has the rectangle formula, is sigma-finite, and is unique.
A jointly measurable latent-variable density is a specified function measurable for and normalized on every parameter fibre: Here is the observed coordinate and the latent coordinate. The observed marginal density is The valid-fibre set is . Only on define the normalized latent-fibre density This definition requires a single jointly measurable density as an input. Likelihood densities supplies neither a sigma-algebra on nor joint parameter measurability from separately specified likelihood sections; the joint measurability above is an additional hypothesis. Because is already supplied as one joint function, this definition uses no choice axiom. It does not assert that AC can turn separately specified pointwise likelihood versions into a jointly measurable version. No quotient or pointwise conditional density is asserted on a zero or infinite marginal fibre.
Depends on
- Finite, sigma-finite, and semifinite measures
- Likelihood densities
- Measurable spaces and measurable sets
- The product sigma-algebra and its finite iterates
- Probability measures and probability spaces
- For sigma-finite factors, the product measure exists, has the rectangle formula, is sigma-finite, and is unique
Used by
- Expectation-maximization Algorithm
- A finite mixture latent factorization Example
- A generalized EM step can increase Q without maximizing it Example
- A support-losing candidate has infinite directional KL Example
- A zero-normalizer latent fiber Example
- An EM likelihood with two strict local maxima Example
- Gaussian mixture likelihood is unbounded under covariance collapse Example
- Responsibilities in a two-component mixture Example
- EM does not decrease the observed log likelihood Theorem
- The observed density is the latent marginal under Tonelli Theorem
Dependency tree · two levels
27 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
- Mario A. T. Figueiredo, Lecture Notes on the EM Algorithm (2004) (standard reference, not scraped)