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.
Descendants of a youngest child are conditionally independent of its parent
Statement
Assume Countable Choice, or suppose the specified noise densities are Borel measurable. Let a finite causally sufficient additive-noise model have graph , and let be an edge such that there is no directed path from to any other child of . Write for the strict descendants of and . Use the supplied Borel noise densities, or fix positive finite Borel versions under Countable Choice, and let be their shifted-noise product density. Then there are positive measurable functions and such that , where does not depend on and does not depend on . Use marginal density versions obtained by iterated integration. Then for almost every . This is the density conditional-independence factorization of and given . Moreover, for every with , the conditional law of given satisfies the density conditional-independence factorization given .
Statement references
Facts & Assumptions
Given: A finite causally sufficient additive-noise model, an edge satisfying the youngest-child condition in the Statement, and its positive joint density.
In a topological order, recursively, and the noises are mutually independent. Continuous additive-noise models on finite DAGs
For supplied Borel noise densities, or positive finite Borel versions chosen under Countable Choice, the selected Borel joint density is , with each factor depending only on that vertex and its parents. Positive joint density of a finite additive-noise model
Nonnegative product-measurable functions can be integrated in any finite coordinate order by iterated sections. Tonelli's theorem for nonnegative measurable functions on a sigma-finite product
Proof
Given: The hypotheses in the Statement.
The Borel noise densities specified in the Statement give the Borel product [F2]; when necessary their versions are supplied under Countable Choice by that same result. Every shifted factor and every finite regrouping is Borel measurable. If were a parent of any , then would be another child of and also a descendant of , contrary to the hypothesis. Thus no vertex in has as a parent. Every parent of a vertex in therefore lies in .
No vertex in can be a parent of a vertex outside : that would make the latter a descendant of . Hence each density factor in [F2] for a vertex outside depends only on , while each factor for a vertex in depends only on . Regrouping the finite product gives for nonnegative measurable functions .
By [F3], the marginal densities obtained from the full product are These identities hold almost everywhere where the marginal densities are finite; Tonelli also permits infinite values on exceptional null sets. Multiplying the last two identities and comparing with the first proves the factorization in the Statement almost everywhere. For any fixed with , put and . Tonelli gives , so for almost every under that conditional law both and are finite and positive. The conditional densities of and given are respectively and ; their product is the joint conditional density. This proves the stated conditional-independence factorization at each such .
Depends on
Used by
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
- Jonas Peters, Joris Mooij, Dominik Janzing, and Bernhard Schölkopf, Causal Discovery with Continuous Additive Noise Models, Appendix A.15 (standard reference, not scraped)
- K. Assaad, E. Devijver, and G. Gaussier, Causal discovery: noise-based methods, ENS Lyon course notes (2023), slides 29–31 (standard reference, not scraped)