Cslib.MachineLearning.PACLearning.IsRPACLearnable.rsampleComplexity_mono_family
theoremverifiedformalizationimported Lean
rsampleComplexity_mono_family for a randomized-learnable class.
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.IsRPACLearnable.rsampleComplexity_mono_family {C : ConceptClass α β} {𝒟 𝒟' : Set (Measure (α × β))} (hL : IsRPACLearnable C 𝒟') (h𝒟 : 𝒟 ⊆ 𝒟') {ε δ : Set.Ioo (0 : ℝ≥0) 1} : rsampleComplexity C ε δ 𝒟 ≤ rsampleComplexity C ε δ 𝒟'
- Formalizes
- CSLib, `Cslib.MachineLearning.PACLearning.IsRPACLearnable.rsampleComplexity_mono_family`
- 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.IsRPACLearnable.rsampleComplexity_mono_family← Cslib.MachineLearning.PACLearning.IsRPACLearnable.rsampleComplexity_mono_family (Cslib/MachineLearning/PACLearning/Defs.lean:463): verbatim
- Verified
- 08 Oct 2026
- Axioms
Classical.choiceQuot.soundpropext- Built on 6
- Cslib.MachineLearning.PACLearning.IsRPACLearnerFor.antitone_familyThe randomized PAC learner predicate is antitone in the distribution family. The universe of the randomness space
Ωis pinned so the… - Cslib.MachineLearning.PACLearning.IsRPACLearnableA concept class
Cis *randomized PAC learnable* over the distribution family𝒟if for every accuracyε ∈ (0, 1)and confidence… - 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.IsRPACLearnerFor
IsRPACLearnerFor m ε δ C 𝒟asserts that there exists a *randomized* learner usingmsamples that is(ε, δ)-correct for the concept… - Cslib.MachineLearning.PACLearning.rsampleComplexityThe *randomized sample complexity* of
C, i.e.sampleComplexityinstantiated at the randomized learner modelIsRPACLearnerFor. The… - 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.IsRPACLearnerFor.antitone_familyThe randomized PAC learner predicate is antitone in the distribution family. The universe of the randomness space
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 /-- `rsampleComplexity_mono_family` for a randomized-learnable class. -/ theorem Cslib.MachineLearning.PACLearning.IsRPACLearnable.rsampleComplexity_mono_family {C : ConceptClass α β} {𝒟 𝒟' : Set (Measure (α × β))} (hL : IsRPACLearnable C 𝒟') (h𝒟 : 𝒟 ⊆ 𝒟') {ε δ : Set.Ioo (0 : ℝ≥0) 1} : rsampleComplexity C ε δ 𝒟 ≤ rsampleComplexity C ε δ 𝒟' := sampleComplexity_le_of_forall (fun h' => h'.antitone_family h𝒟) (hL ε δ)