Cslib.MachineLearning.PACLearning.empiricalMiscount
defimported Lean
The *empirical miscount* of a hypothesis h on a labeled sample S: the number of sample points where h predicts incorrectly.
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 def Cslib.MachineLearning.PACLearning.empiricalMiscount [DecidableEq β] {m : ℕ} (h : α → β) (S : LabeledSample α β m) : ℕ
- Defined in
- CSLib, `Cslib.MachineLearning.PACLearning.empiricalMiscount`
- 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.empiricalMiscount← Cslib.MachineLearning.PACLearning.empiricalMiscount (Cslib/MachineLearning/PACLearning/VersionSpace.lean:114): 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.mem_versionSpace_iff_empiricalMiscount_zeroVersion-space membership equals concept-class membership plus zero empirical miscount (combinatorial bridge).
- Cslib.MachineLearning.PACLearning.empiricalError_eq_divThe empirical 0-1 error equals the empirical miscount divided by the sample size.
- Cslib.MachineLearning.PACLearning.IsConsistent.empiricalMiscount_eq_zeroA consistent learner has zero empirical miscount on every sample.
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 /-- The *empirical miscount* of a hypothesis `h` on a labeled sample `S`: the number of sample points where `h` predicts incorrectly. -/ def Cslib.MachineLearning.PACLearning.empiricalMiscount [DecidableEq β] {m : ℕ} (h : α → β) (S : LabeledSample α β m) : ℕ := (Finset.univ.filter fun i : Fin m => h (S i).1 ≠ (S i).2).card