Cslib.MachineLearning.PACLearning.LearnerModel
abbrevimported Lean
A *learner model* is a predicate on (sample size, accuracy, confidence, concept class, distribution family) that classifies which sample sizes admit a learner of the given kind. Instantiating with IsPACLearnerFor gives the deterministic model; with IsRPACLearnerFor gives the randomized one.
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 abbrev Cslib.MachineLearning.PACLearning.LearnerModel (α β : Type*) [MeasurableSpace α] [MeasurableSpace β]
- Defined in
- CSLib, `Cslib.MachineLearning.PACLearning.LearnerModel`
- 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.LearnerModel← Cslib.MachineLearning.PACLearning.LearnerModel (Cslib/MachineLearning/PACLearning/Defs.lean:329): verbatim
- Verified
- 08 Oct 2026
- Axioms
- none listed
- Built on 1
- 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.ConceptClassA *concept class* over domain
- Used by 2
- Cslib.MachineLearning.PACLearning.sampleComplexityThe *sample complexity* of a concept class
Cunder a learner modelL, at accuracyε ∈ (0, 1)and confidenceδ ∈ (0, 1)over… - 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.sampleComplexityThe *sample complexity* of a concept class
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 *learner model* is a predicate on (sample size, accuracy, confidence, concept class, distribution family) that classifies which sample sizes admit a learner of the given kind. Instantiating with `IsPACLearnerFor` gives the deterministic model; with `IsRPACLearnerFor` gives the randomized one. -/ noncomputable abbrev Cslib.MachineLearning.PACLearning.LearnerModel (α β : Type*) [MeasurableSpace α] [MeasurableSpace β] := ℕ → Set.Ioo (0 : ℝ≥0) 1 → Set.Ioo (0 : ℝ≥0) 1 → ConceptClass α β → Set (Measure (α × β)) → Prop