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.
One-sided coordinate Rademacher contraction
Statement
Let , let be fixed points in a set , and let be a nonempty class of functions . For each , let be -Lipschitz for one common . Suppose either that is finite or countable, or that it has a specified nonempty countable subclass for which, for every sign vector , both displayed suprema equal the corresponding suprema over . Assume the suprema are finite. With independent uniform signs and the one-sided normalization
one has
No condition is required.
Statement references
One-sided empirical Rademacher complexity: fixes the nonabsolute sign supremum and normalization.
One-sided coordinate Rademacher contraction: proves this inequality for finite or countable classes, including the no-zero-at-zero case.
Mohri et al., Lemma 5.7, printed pp. 93–94: states the coordinatewise one-sided factor- contraction under the same normalization.
Bartlett and Mendelson, Theorem 12(4), printed p. 469: uses a different absolute-value convention, assumes the scalar map vanishes at zero, and has factor ; that convention is not used here.
Facts & Assumptions
Given: A fixed sample, a nonempty real-valued class, common Lipschitz constant , and finite sign suprema.
The one-sided empirical Rademacher complexity is , with no absolute value. One-sided empirical Rademacher complexity
For a finite class, or a countable class with finite sign suprema, coordinatewise -Lipschitz maps satisfy without requiring . One-sided coordinate Rademacher contraction
Proof
Given: The objects and hypotheses in the Statement.
If is finite or countable, [F1] identifies the right-hand side with the published supplier's one-sided normalization, and [F2] gives the inequality with exactly the stated common Lipschitz constant and no zero-at-zero assumption.
Otherwise, use the specified countable subclass . For every sign vector, its transformed and untransformed suprema equal those over by hypothesis; averaging over the finite sign space therefore gives the same two quantities. Applying step 1.1 to proves the displayed inequality for .
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
- Mehryar Mohri, Afshin Rostamizadeh, and Ameet Talwalkar, Foundations of Machine Learning, 2nd ed., Lemma 5.7 (standard reference, not scraped)
- Peter L. Bartlett and Shahar Mendelson, Rademacher and Gaussian Complexities: Risk Bounds and Structural Results, JMLR 3 (2002), Theorem 12(4) (standard reference, not scraped)