Cslib.MachineLearning.PACLearning.SetShatters
defimported Lean
A binary concept class C *shatters* a set W if for every subset W' ⊆ W, there exists a concept c ∈ C whose positive set c ⁻¹' {true} intersects W in exactly W'.
Statement
set_option autoImplicit true in set_option relaxedAutoImplicit true in open Set in variable {α : Type*} in def Cslib.MachineLearning.PACLearning.SetShatters (C : ConceptClass α Bool) (W : Set α) : Prop
- Defined in
- CSLib, `Cslib.MachineLearning.PACLearning.SetShatters`
- 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← Cslib.MachineLearning.PACLearning.SetShatters (Cslib/MachineLearning/PACLearning/VCDimension.lean:53): verbatim
- Verified
- 08 Oct 2026
- Axioms
- none listed
- Built on 1
- 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.ConceptClassA *concept class* over domain
- Used by 5
- Cslib.MachineLearning.PACLearning.hasFiniteVCDim_iffA class has finite VC dimension iff there is a uniform bound on the cardinality of every shattered finite set.
- Cslib.MachineLearning.PACLearning.HasFiniteVCDimA binary concept class
Chas *finite VC dimension* if there is a uniform upper bound on the cardinalities of finite sets it shatters.… - Cslib.MachineLearning.PACLearning.SetShatters.subsetShattering is anti-monotone in the shattered set: if
CshattersWandV ⊆ W, thenCshattersV. - Cslib.MachineLearning.PACLearning.vcDimThe *Vapnik-Chervonenkis dimension* of a binary concept class
Cis the supremum of the cardinalities of finite sets shattered byC.… - Cslib.MachineLearning.PACLearning.SetShatters.supersetShattering is monotone in the concept class: if
CshattersWandC ⊆ C', thenC'shattersW.
Lean source view module on GitHub
set_option autoImplicit true in set_option relaxedAutoImplicit true in open Set in variable {α : Type*} in /-- A binary concept class `C` *shatters* a set `W` if for every subset `W' ⊆ W`, there exists a concept `c ∈ C` whose positive set `c ⁻¹' {true}` intersects `W` in exactly `W'`. -/ def Cslib.MachineLearning.PACLearning.SetShatters (C : ConceptClass α Bool) (W : Set α) : Prop := ∀ W' ⊆ W, ∃ c ∈ C, c ⁻¹' {true} ∩ W = W'