Cslib.MachineLearning.PACLearning.IsPACLearnable.sampleComplexity_mono_C
theoremverifiedformalizationimported Lean
sampleComplexity_mono_C for a learnable class (learnability at the *larger* class C' is the hypothesis).
Statement
set_option autoImplicit true in set_option relaxedAutoImplicit true in open MeasureTheory Set in open scoped ENNReal NNReal in variable {α : Type*} {β : Type*} [MeasurableSpace α] [MeasurableSpace β] in theorem Cslib.MachineLearning.PACLearning.IsPACLearnable.sampleComplexity_mono_C {C C' : ConceptClass α β} {𝒟 : Set (Measure (α × β))} (hL : IsPACLearnable C' 𝒟) (hC : C ⊆ C') {ε δ : Set.Ioo (0 : ℝ≥0) 1} : sampleComplexity IsPACLearnerFor C ε δ 𝒟 ≤ sampleComplexity IsPACLearnerFor C' ε δ 𝒟
- Formalizes
- CSLib, `Cslib.MachineLearning.PACLearning.IsPACLearnable.sampleComplexity_mono_C`
- 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.IsPACLearnable.sampleComplexity_mono_C← Cslib.MachineLearning.PACLearning.IsPACLearnable.sampleComplexity_mono_C (Cslib/MachineLearning/PACLearning/Defs.lean:449): verbatim
- Verified
- 08 Oct 2026
- Axioms
Classical.choiceQuot.soundpropext- Built on 6
- Cslib.MachineLearning.PACLearning.IsPACLearnerFor
IsPACLearnerFor m ε δ C 𝒟asserts that there exists a learner usingmsamples that is(ε, δ)-correct for the concept classCover… - Cslib.MachineLearning.PACLearning.sampleComplexityThe *sample complexity* of a concept class
Cunder a learner modelL, at accuracyε ∈ (0, 1)and confidenceδ ∈ (0, 1)over… - 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.IsPACLearnableA concept class
Cis *PAC learnable* over the distribution family𝒟if for every accuracyε ∈ (0, 1)and confidenceδ ∈ (0, 1),… - Cslib.MachineLearning.PACLearning.sampleComplexity_le_of_forallGeneral pointwise monotonicity of
sampleComplexity: if every witness sample size for(L₁, ε₁, δ₁, C₁, 𝒟₁)is also a witness for… - Cslib.MachineLearning.PACLearning.IsPACLearnerFor.antitone_CThe deterministic PAC learner predicate is antitone in the concept class: a learner for a larger class
C'is also a learner for any…
- Cslib.MachineLearning.PACLearning.IsPACLearnerFor
Lean source view module on GitHub
set_option autoImplicit true in set_option relaxedAutoImplicit true in open MeasureTheory Set in open scoped ENNReal NNReal in variable {α : Type*} {β : Type*} [MeasurableSpace α] [MeasurableSpace β] in /-- `sampleComplexity_mono_C` for a learnable class (learnability at the *larger* class `C'` is the hypothesis). -/ theorem Cslib.MachineLearning.PACLearning.IsPACLearnable.sampleComplexity_mono_C {C C' : ConceptClass α β} {𝒟 : Set (Measure (α × β))} (hL : IsPACLearnable C' 𝒟) (hC : C ⊆ C') {ε δ : Set.Ioo (0 : ℝ≥0) 1} : sampleComplexity IsPACLearnerFor C ε δ 𝒟 ≤ sampleComplexity IsPACLearnerFor C' ε δ 𝒟 := sampleComplexity_le_of_forall (fun h' => h'.antitone_C hC) (hL ε δ)