AFTD Auto-Formalizing Theoretical Domains

Cslib.MachineLearning.PACLearning.hasFiniteVCDim_iff

theoremverifiedformalizationimported Lean

A class has finite VC dimension iff there is a uniform bound on the cardinality of every shattered finite set.

Statement

set_option autoImplicit true in
set_option relaxedAutoImplicit true in
open Set in
variable {α : Type*} in
theorem Cslib.MachineLearning.PACLearning.hasFiniteVCDim_iff {C : ConceptClass α Bool} :
    HasFiniteVCDim C ↔ ∃ N : ℕ, ∀ W : Finset α, SetShatters C ↑W → W.card ≤ N
Formalizes
CSLib, `Cslib.MachineLearning.PACLearning.hasFiniteVCDim_iff`
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.
Verified
08 Oct 2026
Axioms
Classical.choiceQuot.soundpropext
Built on 3

Lean source view module on GitHub

set_option autoImplicit true in
set_option relaxedAutoImplicit true in
open Set in
variable {α : Type*} in
/-- A class has finite VC dimension iff there is a uniform bound on the cardinality of every shattered finite set. -/
theorem Cslib.MachineLearning.PACLearning.hasFiniteVCDim_iff {C : ConceptClass α Bool} :
    HasFiniteVCDim C ↔ ∃ N : ℕ, ∀ W : Finset α, SetShatters C ↑W → W.card ≤ N :=
  ⟨fun ⟨N, hN⟩ => ⟨N, fun W hW => hN ⟨W, rfl, hW⟩⟩,
   fun ⟨N, hN⟩ => ⟨N, fun _ ⟨W, hWc, hW⟩ => hWc ▸ hN W hW⟩⟩
See it in the graphDiscuss this resultChallenge it