Cslib.MachineLearning.PACLearning.versionSpace_antitone
theoremverifiedformalizationimported Lean
*Version space antitonicity.* Given a sample of size n and m ≤ n, the version space on all n observations is a subset of the version space on the first m observations. Special case of versionSpace_reindex with f := Fin.castLE hmn.
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.versionSpace_antitone {m n : ℕ} (hmn : m ≤ n) (C : ConceptClass α β) (S : LabeledSample α β n) : VersionSpace C S ⊆ VersionSpace C (S ∘ Fin.castLE hmn)
- Formalizes
- CSLib, `Cslib.MachineLearning.PACLearning.versionSpace_antitone`
- 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.versionSpace_antitone← Cslib.MachineLearning.PACLearning.versionSpace_antitone (Cslib/MachineLearning/PACLearning/VersionSpace.lean:99): verbatim
- Verified
- 08 Oct 2026
- Axioms
- none — Lean reports it depends on no axioms
- Built on 4
- 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.versionSpace_reindex*Version space reindexing.* For any reindexing
f : Fin m → Fin n, the version space onSis contained in the version space on the…
- Cslib.MachineLearning.PACLearning.LabeledSampleA *labeled sample* of size
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 /-- *Version space antitonicity.* Given a sample of size `n` and `m ≤ n`, the version space on all `n` observations is a subset of the version space on the first `m` observations. Special case of `versionSpace_reindex` with `f := Fin.castLE hmn`. -/ theorem Cslib.MachineLearning.PACLearning.versionSpace_antitone {m n : ℕ} (hmn : m ≤ n) (C : ConceptClass α β) (S : LabeledSample α β n) : VersionSpace C S ⊆ VersionSpace C (S ∘ Fin.castLE hmn) := versionSpace_reindex (Fin.castLE hmn) C S