Cslib.MachineLearning.PACLearning.IsPACLearnerFor.toIsRPACLearnerFor
theoremverifiedformalizationimported Lean
Every deterministic PAC learner is in particular a randomized PAC learner (with the trivial one-point randomness space PUnit).
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.toIsRPACLearnerFor {m : ℕ} {ε δ : Set.Ioo (0 : ℝ≥0) 1} {C : ConceptClass α β} {𝒟 : Set (Measure (α × β))} (h : IsPACLearnerFor m ε δ C 𝒟) : IsRPACLearnerFor m ε δ C 𝒟
- Formalizes
- CSLib, `Cslib.MachineLearning.PACLearning.IsPACLearnerFor.toIsRPACLearnerFor`
- 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.IsPACLearnerFor.toIsRPACLearnerFor← Cslib.MachineLearning.PACLearning.IsPACLearnerFor.toIsRPACLearnerFor (Cslib/MachineLearning/PACLearning/Defs.lean:195): verbatim
- Verified
- 08 Oct 2026
- Axioms
Classical.choiceQuot.soundpropext- Built on 7
- 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.errorThe *prediction error* (0-1 loss) of a hypothesis
hunder a joint distributionDonα × β, defined as the probability that the… - Cslib.MachineLearning.PACLearning.LabeledSampleA *labeled sample* of size
mover domainαwith label typeβis a finite sequence of(point, label)pairs. - Cslib.MachineLearning.PACLearning.optimalErrorThe *optimal error* of a concept class
Cunder a joint distributionD, defined as the infimum oferror D cover all concepts… - 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.LearnerA *learner* using
msamples is a function that takes a labeled sample and produces a hypothesis (a function from the domain to the label…
- Cslib.MachineLearning.PACLearning.IsPACLearnerFor
- Used by 1
- Cslib.MachineLearning.PACLearning.IsPACLearnable.toIsRPACLearnableDeterministic PAC learnability implies randomized PAC learnability.
Lean source view module on GitHub
Choose a tactic — a marked line — to see the goals Lean had before and after it, as in Lean’s infoview. Step with ← → or j k.
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/-- Every deterministic PAC learner is in particular a randomized PAC learner (with the trivial one-point randomness space `PUnit`). -/theorem Cslib.MachineLearning.PACLearning.IsPACLearnerFor.toIsRPACLearnerFor {m : ℕ} {ε δ : Set.Ioo (0 : ℝ≥0) 1} {C : ConceptClass α β} {𝒟 : Set (Measure (α × β))} (h : IsPACLearnerFor m ε δ C 𝒟) : IsRPACLearnerFor m ε δ C 𝒟 := by obtain ⟨A, hA⟩ := h refine ⟨PUnit, inferInstance, Measure.dirac PUnit.unit, inferInstance, fun _ => A, ?_⟩ intro D _ hD refine ⟨measurable_const.aemeasurable, ?_⟩ simp only [gt_iff_lt, lintegral_const, measure_univ, mul_one] exact hA D hD