AFTD Auto-Formalizing Theoretical Domains

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.
Verified
08 Oct 2026
Axioms
none listed
Built on 2
Used by 4

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
See it in the graphDiscuss this resultChallenge it