AFTD Auto-Formalizing Theoretical Domains

Cslib.MachineLearning.PACLearning.IsConsistent.output_agrees

theoremverifiedformalizationimported Lean

A consistent learner's output agrees with the sample on every observed point.

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.IsConsistent.output_agrees {m : ℕ} {A : Learner α β m}
    {C : ConceptClass α β} (hA : IsConsistent A C) (S : LabeledSample α β m)
    (i : Fin m) :
    A S (S i).1 = (S i).2
Formalizes
CSLib, `Cslib.MachineLearning.PACLearning.IsConsistent.output_agrees`
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 — Lean reports it depends on no axioms
Built on 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 consistent learner's output agrees with the sample on every observed point. -/
theorem Cslib.MachineLearning.PACLearning.IsConsistent.output_agrees {m : ℕ} {A : Learner α β m}
    {C : ConceptClass α β} (hA : IsConsistent A C) (S : LabeledSample α β m)
    (i : Fin m) :
    A S (S i).1 = (S i).2 := (hA S).2 i
See it in the graphDiscuss this resultChallenge it