Cslib.MachineLearning.PACLearning.empiricalMeasure
defimported Lean
The *empirical distribution* of a labeled sample: the uniform mixture of Dirac measures at each sample point. Equals the zero measure when m = 0.
Statement
set_option autoImplicit true in set_option relaxedAutoImplicit true in open MeasureTheory Set in open scoped ENNReal in variable {α : Type*} {β : Type*} in variable [MeasurableSpace α] [MeasurableSpace β] in noncomputable def Cslib.MachineLearning.PACLearning.empiricalMeasure {m : ℕ} (S : LabeledSample α β m) : Measure (α × β)
- Defined in
- CSLib, `Cslib.MachineLearning.PACLearning.empiricalMeasure`
- Lean proof
- By Dhruv Gupta, from github.com/leanprover/cslib at
3951377e5a3f(Copyright (c) 2026 Dhruv Gupta. 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.empiricalMeasure← Cslib.MachineLearning.PACLearning.empiricalMeasure (Cslib/MachineLearning/PACLearning/VersionSpace.lean:123): verbatim
- Verified
- 08 Oct 2026
- Axioms
- none listed
- Built on 1
- Cslib.MachineLearning.PACLearning.LabeledSampleA *labeled sample* of size
mover domainαwith label typeβis a finite sequence of(point, label)pairs.
- Cslib.MachineLearning.PACLearning.LabeledSampleA *labeled sample* of size
- Used by 3
- Cslib.MachineLearning.PACLearning.empiricalErrorThe *empirical 0-1 error* of
honS: the empirical distribution's mass on the disagreement set. - Cslib.MachineLearning.PACLearning.empiricalError_eq_divThe empirical 0-1 error equals the empirical miscount divided by the sample size.
- Cslib.MachineLearning.PACLearning.mem_versionSpace_iff_empiricalError_zeroVersion-space membership equals concept-class membership plus zero empirical error (measure-theoretic bridge).
- Cslib.MachineLearning.PACLearning.empiricalErrorThe *empirical 0-1 error* of
Lean source view module on GitHub
set_option autoImplicit true in set_option relaxedAutoImplicit true in open MeasureTheory Set in open scoped ENNReal in variable {α : Type*} {β : Type*} in variable [MeasurableSpace α] [MeasurableSpace β] in /-- The *empirical distribution* of a labeled sample: the uniform mixture of Dirac measures at each sample point. Equals the zero measure when `m = 0`. -/ noncomputable def Cslib.MachineLearning.PACLearning.empiricalMeasure {m : ℕ} (S : LabeledSample α β m) : Measure (α × β) := if _hm : m = 0 then 0 else (m : ℝ≥0∞)⁻¹ • ∑ i, Measure.dirac (S i)