AFTD Auto-Formalizing Theoretical Domains

Cslib.MachineLearning.PACLearning.IsPACLearnerFor.antitone_family

theoremverifiedformalizationimported Lean

The deterministic PAC learner predicate is antitone in the distribution family: a learner for a larger family 𝒟' is also a learner for any subfamily 𝒟 ⊆ 𝒟'.

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.IsPACLearnerFor.antitone_family {m : ℕ} {ε δ : Set.Ioo (0 : ℝ≥0) 1}
    {C : ConceptClass α β} {𝒟 𝒟' : Set (Measure (α × β))}
    (h𝒟 : 𝒟 ⊆ 𝒟') (h : IsPACLearnerFor m ε δ C 𝒟') :
    IsPACLearnerFor m ε δ C 𝒟
Formalizes
CSLib, `Cslib.MachineLearning.PACLearning.IsPACLearnerFor.antitone_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.
Verified
08 Oct 2026
Axioms
Classical.choiceQuot.soundpropext
Built on 6
Used by 3

Lean source view module on GitHub

set_option autoImplicit true inset_option relaxedAutoImplicit true inopen MeasureTheory Set inopen scoped ENNReal NNReal invariable {α : Type*} {β : Type*} [MeasurableSpace α] [MeasurableSpace β] in/-- The deterministic PAC learner predicate is antitone in the distribution family: a learner for a larger family `𝒟'` is also a learner for any subfamily `𝒟 ⊆ 𝒟'`. -/theorem Cslib.MachineLearning.PACLearning.IsPACLearnerFor.antitone_family {m : ℕ} {ε δ : Set.Ioo (0 : ℝ≥0) 1}    {C : ConceptClass α β} {𝒟 𝒟' : Set (Measure (α × β))}    (h𝒟 : 𝒟 ⊆ 𝒟') (h : IsPACLearnerFor m ε δ C 𝒟') :    IsPACLearnerFor m ε δ C 𝒟 := by  obtain ⟨A, hA⟩ := h  exact ⟨A, fun D inst hD => @hA D inst (h𝒟 hD)⟩
See it in the graphDiscuss this resultChallenge it