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.
Locally essentially bounded activations with null discontinuity closure
Definition
Assume Countable Choice for the Lebesgue-measure convention. A real-valued function belongs to the activation class when it is Lebesgue measurable, is locally essentially bounded, and the closure of its discontinuity set has one-dimensional Lebesgue measure zero. Here locally essentially bounded means that for every compact interval there is a finite such that for Lebesgue-almost every . The discontinuity set is . The function is a polynomial almost everywhere when there is a real algebraic polynomial such that outside a Lebesgue-null set.
The subclass consists of those that are also pointwise locally bounded: for every compact interval . This extra condition distinguishes pointwise uniform approximation from approximation in the essential-supremum norm.
Depends on
Used by
- A one-neuron kernel has convergent uniform quadratures and divergent C1 quadratures Counterexample
- Essential boundedness does not imply pointwise uniform universality Counterexample
- ReLU and logistic sigmoid activation examples Example
- Networks approximate smooth convolutions of the activation Lemma
- Polynomial activation convolutions have a common degree bound Lemma
- Polynomial convolutions force activation polynomiality almost everywhere Lemma
- Rough nonpolynomial activations are dense on compact sets Lemma
- Neural operators approximate continuous maps uniformly on compacta Theorem
- Single-hidden-layer universal approximation Theorem
Dependency tree · two levels
13 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, Definitions 3–5 and §4 (standard reference, not scraped)
- Moreau, Dynamical Neural Networks and Composition Networks for System Modeling, Chapter 2 §2.3 (standard reference, not scraped)