Cslib.MachineLearning.PACLearning.HasFiniteVCDim
defimported Lean
A binary concept class C has *finite VC dimension* if there is a uniform upper bound on the cardinalities of finite sets it shatters. This is the hypothesis under which vcDim C is mathematically meaningful (otherwise vcDim returns 0 for unbounded shattered families via sSup on ℕ).
Statement
set_option autoImplicit true in set_option relaxedAutoImplicit true in open Set in variable {α : Type*} in def Cslib.MachineLearning.PACLearning.HasFiniteVCDim (C : ConceptClass α Bool) : Prop
- Defined in
- CSLib, `Cslib.MachineLearning.PACLearning.HasFiniteVCDim`
- 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.HasFiniteVCDim← Cslib.MachineLearning.PACLearning.HasFiniteVCDim (Cslib/MachineLearning/PACLearning/VCDimension.lean:118): verbatim
- Verified
- 08 Oct 2026
- Axioms
- none listed
- 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
- Used by 1
- Cslib.MachineLearning.PACLearning.hasFiniteVCDim_iffA class has finite VC dimension iff there is a uniform bound on the cardinality of every shattered finite set.
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` has *finite VC dimension* if there is a uniform upper bound on the cardinalities of finite sets it shatters. This is the hypothesis under which `vcDim C` is mathematically meaningful (otherwise `vcDim` returns `0` for unbounded shattered families via `sSup` on `ℕ`). -/ def Cslib.MachineLearning.PACLearning.HasFiniteVCDim (C : ConceptClass α Bool) : Prop := BddAbove {n : ℕ | ∃ W : Finset α, W.card = n ∧ SetShatters C (↑W)}