Cslib.MachineLearning.PACLearning.mem_versionSpace_of_realizable
theoremverifiedformalizationimported Lean
*Realizable version-space nonemptiness.* If a target concept c lies in C and the sample S is labeled by c (i.e. every (S i).2 = c (S i).1), then c itself lies in the version space VersionSpace C S.
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.mem_versionSpace_of_realizable {m : ℕ} {C : ConceptClass α β} {c : α → β} (hc : c ∈ C) (S : LabeledSample α β m) (hS : ∀ i : Fin m, (S i).2 = c (S i).1) : c ∈ VersionSpace C S
- Formalizes
- CSLib, `Cslib.MachineLearning.PACLearning.mem_versionSpace_of_realizable`
- 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.mem_versionSpace_of_realizable← Cslib.MachineLearning.PACLearning.mem_versionSpace_of_realizable (Cslib/MachineLearning/PACLearning/VersionSpace.lean:219): verbatim
- Verified
- 08 Oct 2026
- Axioms
- none — Lean reports it depends on no axioms
- Built on 3
- Cslib.MachineLearning.PACLearning.LabeledSampleA *labeled sample* of size
mover domainαwith label typeβis a finite sequence of(point, label)pairs. - Cslib.MachineLearning.PACLearning.VersionSpaceThe *version space* of a concept class
Cgiven a labeled sampleS: the set of concepts inCwhose labels agree withSon every… - Cslib.MachineLearning.PACLearning.ConceptClassA *concept class* over domain
αwith label typeβis a set of functionsα → β. For binary classification (β = Bool), this is…
- Cslib.MachineLearning.PACLearning.LabeledSampleA *labeled sample* of size
- Used by 1
- Cslib.MachineLearning.PACLearning.Realizable.versionSpace_nonemptyA realizable sample has nonempty version space.
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 /-- *Realizable version-space nonemptiness.* If a target concept `c` lies in `C` and the sample `S` is labeled by `c` (i.e. every `(S i).2 = c (S i).1`), then `c` itself lies in the version space `VersionSpace C S`. -/ theorem Cslib.MachineLearning.PACLearning.mem_versionSpace_of_realizable {m : ℕ} {C : ConceptClass α β} {c : α → β} (hc : c ∈ C) (S : LabeledSample α β m) (hS : ∀ i : Fin m, (S i).2 = c (S i).1) : c ∈ VersionSpace C S := ⟨hc, fun i => (hS i).symm⟩