Cslib.MachineLearning.PACLearning.IsRPACLearnable
defimported Lean
A concept class C is *randomized PAC learnable* over the distribution family 𝒟 if for every accuracy ε ∈ (0, 1) and confidence δ ∈ (0, 1), there exists a sample size m admitting a randomized (ε, δ)-PAC learner for C. The randomness space is pinned to Type 0 at the learnability level; IsRPACLearnerFor itself remains universe-polymorphic.
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 noncomputable def Cslib.MachineLearning.PACLearning.IsRPACLearnable (C : ConceptClass α β) (𝒟 : Set (Measure (α × β))) : Prop
- Defined in
- CSLib, `Cslib.MachineLearning.PACLearning.IsRPACLearnable`
- 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← Cslib.MachineLearning.PACLearning.IsRPACLearnable (Cslib/MachineLearning/PACLearning/Defs.lean:293): verbatim
- Verified
- 08 Oct 2026
- Axioms
- none listed
- Built on 2
- 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.ConceptClassA *concept class* over domain
- Used by 4
- Cslib.MachineLearning.PACLearning.IsRPACLearnable.rsampleComplexity_mono_family
rsampleComplexity_mono_familyfor a randomized-learnable class. - Cslib.MachineLearning.PACLearning.IsRPACLearnable.antitone_familyRandomized PAC learnability is antitone in the distribution family.
- Cslib.MachineLearning.PACLearning.IsRPACLearnable.rsampleComplexity_antitone_δ
rsampleComplexity_antitone_δfor a randomized-learnable class. - Cslib.MachineLearning.PACLearning.IsPACLearnable.toIsRPACLearnableDeterministic PAC learnability implies randomized PAC learnability.
- Cslib.MachineLearning.PACLearning.IsRPACLearnable.rsampleComplexity_mono_family
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 /-- A concept class `C` is *randomized PAC learnable* over the distribution family `𝒟` if for every accuracy `ε ∈ (0, 1)` and confidence `δ ∈ (0, 1)`, there exists a sample size `m` admitting a randomized `(ε, δ)`-PAC learner for `C`. The randomness space is pinned to `Type 0` at the learnability level; `IsRPACLearnerFor` itself remains universe-polymorphic. -/ noncomputable def Cslib.MachineLearning.PACLearning.IsRPACLearnable (C : ConceptClass α β) (𝒟 : Set (Measure (α × β))) : Prop := ∀ (ε δ : Set.Ioo (0 : ℝ≥0) 1), ∃ m, IsRPACLearnerFor.{_, _, 0} m ε δ C 𝒟