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.
Polynomial ridge functions are dense on compact sets
Statement
Let and let be compact. Let be the real linear span of the functions with and , using the convention for every real . Then the restrictions are uniformly dense in .
Statement references
Facts & Assumptions
Given: An integer and a compact set .
Every unital point-separating real function algebra on a compact Hausdorff space is uniformly dense in the continuous real-valued functions (Real Stone–Weierstrass theorem for compact Hausdorff spaces).
Proof
Fix and linear forms for . Expanding the powers and summing signs gives the polarization identity . Indeed, in the multinomial expansion, a monomial has sign sum , which is zero unless every is odd. Since , the only surviving tuple is , with coefficient . Thus every product of linear forms lies in .
Every coordinate monomial of positive total degree is a product of coordinate linear forms, with repeated times. Step 1.1 puts it in . Constants lie in by , so every real polynomial restricts to an element of .
The restrictions to of real polynomials form a unital real function algebra: sums, scalar multiples, and products are polynomials, and the constant-one polynomial is a unit. If are distinct, some coordinate differs, so the corresponding coordinate polynomial separates them. By [F1] these polynomial restrictions are uniformly dense in . Since step 2.1 places them inside , the latter is dense as well.
Depends on
Used by
Dependency tree · two levels
3 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
- Leshno, Lin, Pinkus, and Schocken, Multilayer Feedforward Networks With a Non-Polynomial Activation Function Can Approximate Any Function, proof of Theorem 1, Step 2 (standard reference, not scraped)
- Moreau, Dynamical Neural Networks and Composition Networks for System Modeling, Chapter 2 §2.3 (standard reference, not scraped)