Cslib.MachineLearning.PACLearning.empiricalError_eq_div
theoremverifiedformalizationimported Lean
The empirical 0-1 error equals the empirical miscount divided by the sample size.
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 theorem Cslib.MachineLearning.PACLearning.empiricalError_eq_div [DecidableEq β] [MeasurableSpace α] [MeasurableSpace β] [MeasurableSingletonClass α] [MeasurableSingletonClass β] {m : ℕ} (hm : 0 < m) (h : α → β) (S : LabeledSample α β m) : empiricalError h S = (empiricalMiscount h S : ℝ≥0∞) / m
- Formalizes
- CSLib, `Cslib.MachineLearning.PACLearning.empiricalError_eq_div`
- 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.empiricalError_eq_div← Cslib.MachineLearning.PACLearning.empiricalError_eq_div (Cslib/MachineLearning/PACLearning/VersionSpace.lean:161): verbatim
- Verified
- 08 Oct 2026
- Axioms
Classical.choiceQuot.soundpropext- Built on 5
- 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.empiricalErrorThe *empirical 0-1 error* of
honS: the empirical distribution's mass on the disagreement set. - Cslib.MachineLearning.PACLearning.empiricalMeasureThe *empirical distribution* of a labeled sample: the uniform mixture of Dirac measures at each sample point. Equals the zero measure when…
- Cslib.MachineLearning.PACLearning.empiricalMiscountThe *empirical miscount* of a hypothesis
hon a labeled sampleS: the number of sample points wherehpredicts incorrectly.
- Cslib.MachineLearning.PACLearning.errorThe *prediction error* (0-1 loss) of a hypothesis
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 invariable {α : Type*} {β : Type*} in/-- The empirical 0-1 error equals the empirical miscount divided by the sample size. -/theorem Cslib.MachineLearning.PACLearning.empiricalError_eq_div [DecidableEq β] [MeasurableSpace α] [MeasurableSpace β] [MeasurableSingletonClass α] [MeasurableSingletonClass β] {m : ℕ} (hm : 0 < m) (h : α → β) (S : LabeledSample α β m) : empiricalError h S = (empiricalMiscount h S : ℝ≥0∞) / m := by have hm_ne : m ≠ 0 := hm.ne' unfold empiricalError empiricalMeasure error empiricalMiscount rw [dif_neg hm_ne, Measure.smul_apply, Measure.finsetSum_apply] simp only [Measure.dirac_apply, Set.indicator, Set.mem_ofPred_eq, Pi.one_apply, smul_eq_mul] rw [Finset.sum_boole, ← ENNReal.div_eq_inv_mul]