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.
Euler identity for Clarke subgradients of homogeneous margins
Statement
Let be locally Lipschitz and positively homogeneous of degree , meaning for every . For every and every , one has for and .
Statement references
Facts & Assumptions
Given: The locally Lipschitz map , its positive homogeneity degree , a nonzero parameter , and the Clarke subdifferential convention.
Clarke subdifferential and gradient-flow trajectory: for locally Lipschitz maps, the Clarke subdifferential is the closed convex hull of limits of ordinary gradients along differentiability points.
Proof
If is differentiable at , then is differentiable at and the homogeneity identity gives for every direction , by writing and taking the difference-quotient limit as .
At every differentiability point , differentiating with respect to at gives .
Conversely, differentiability at implies differentiability at by applying the same argument with scale . Thus scaling by bijects the differentiability points and sends each gradient to times that gradient. Taking all gradient limits as , and then their closed convex hull as in [F1], proves .
For any gradient limit with differentiability points , continuity of gives . This identity is preserved by convex combinations and limits, so [F1] yields it for every .
Depends on
Used by
Dependency tree · one level
1 result within one dependency step 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
- Kaifeng Lyu and Jian Li, Gradient Descent Maximizes the Margin of Homogeneous Neural Networks, Theorem B.2 (standard reference, not scraped)