AFTD Auto-Formalizing Theoretical Domains

Cslib.MachineLearning.PACLearning.empiricalError

defimported Lean

The *empirical 0-1 error* of h on S: the empirical distribution's mass on the disagreement set.

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.empiricalError {m : ℕ} (h : α → β) (S : LabeledSample α β m) :
    ℝ≥0∞
Defined in
CSLib, `Cslib.MachineLearning.PACLearning.empiricalError`
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.
Verified
08 Oct 2026
Axioms
none listed
Built on 3
Used by 3

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 0-1 error* of `h` on `S`: the empirical distribution's mass on the disagreement set. -/
noncomputable def Cslib.MachineLearning.PACLearning.empiricalError {m : ℕ} (h : α → β) (S : LabeledSample α β m) :
    ℝ≥0∞ :=
  error (empiricalMeasure S) h
See it in the graphDiscuss this resultChallenge it