Cslib.MachineLearning.PACLearning.SetShatters.superset
theoremverifiedformalizationimported Lean
Shattering is monotone in the concept class: if C shatters W and C ⊆ C', then C' shatters W.
Statement
set_option autoImplicit true in set_option relaxedAutoImplicit true in open Set in variable {α : Type*} in theorem Cslib.MachineLearning.PACLearning.SetShatters.superset {C C' : ConceptClass α Bool} {W : Set α} (hW : SetShatters C W) (hCC' : C ⊆ C') : SetShatters C' W
- Formalizes
- CSLib, `Cslib.MachineLearning.PACLearning.SetShatters.superset`
- Lean proof
- By Samuel Schlesinger, from github.com/leanprover/cslib at
3951377e5a3f(Copyright (c) 2026 Samuel Schlesinger. All rights reserved, Apache-2.0). Compiled here against leanprover/lean4:v4.33.1, Mathlib v4.33.1; written for leanprover/lean4:v4.33.0.Cslib.MachineLearning.PACLearning.SetShatters.superset← Cslib.MachineLearning.PACLearning.SetShatters.superset (Cslib/MachineLearning/PACLearning/VCDimension.lean:75): verbatim
- Verified
- 08 Oct 2026
- Axioms
- none — Lean reports it depends on no axioms
- Built on 2
- Cslib.MachineLearning.PACLearning.ConceptClassA *concept class* over domain
αwith label typeβis a set of functionsα → β. For binary classification (β = Bool), this is… - Cslib.MachineLearning.PACLearning.SetShattersA binary concept class
C*shatters* a setWif for every subsetW' ⊆ W, there exists a conceptc ∈ Cwhose positive set…
- Cslib.MachineLearning.PACLearning.ConceptClassA *concept class* over domain
Lean source view module on GitHub
Choose a tactic — a marked line — to see the goals Lean had before and after it, as in Lean’s infoview. Step with ← → or j k.
set_option autoImplicit true inset_option relaxedAutoImplicit true inopen Set invariable {α : Type*} in/-- Shattering is monotone in the concept class: if `C` shatters `W` and `C ⊆ C'`, then `C'` shatters `W`. -/theorem Cslib.MachineLearning.PACLearning.SetShatters.superset {C C' : ConceptClass α Bool} {W : Set α} (hW : SetShatters C W) (hCC' : C ⊆ C') : SetShatters C' W := by intro W' hW' obtain ⟨c, hc, hcW⟩ := hW W' hW' exact ⟨c, hCC' hc, hcW⟩