AFTD Auto-Formalizing Theoretical Domains

Cslib.MachineLearning.PACLearning.IsConsistent

defimported Lean

A learner is *consistent* with the concept class C if, on every labeled sample it receives, its output hypothesis lies in the version space of C at that sample — i.e. the output is in C and agrees with every observed labeled pair.

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.IsConsistent {m : ℕ} (A : Learner α β m) (C : ConceptClass α β) : Prop
Defined in
CSLib, `Cslib.MachineLearning.PACLearning.IsConsistent`
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 4
Used by 4

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
/-- A learner is *consistent* with the concept class `C` if, on every labeled sample it receives, its output hypothesis lies in the version space of `C` at that sample — i.e. the output is in `C` and agrees with every observed labeled pair. -/
def Cslib.MachineLearning.PACLearning.IsConsistent {m : ℕ} (A : Learner α β m) (C : ConceptClass α β) : Prop :=
  ∀ S : LabeledSample α β m, A S ∈ VersionSpace C S
See it in the graphDiscuss this resultChallenge it