Cslib.MachineLearning.PACLearning.versionSpace_append
theoremverifiedformalizationimported Lean
*The version-space meet law.* The version space of an appended sample is the intersection of the version spaces of the two parts: constraints accumulate by intersection.
Statement
set_option autoImplicit true in set_option relaxedAutoImplicit true in open Set in variable {α : Type*} {β : Type*} in theorem Cslib.MachineLearning.PACLearning.versionSpace_append {m n : ℕ} (C : ConceptClass α β) (S : LabeledSample α β m) (T : LabeledSample α β n) : VersionSpace C (Fin.append S T) = VersionSpace C S ∩ VersionSpace C T
- Formalizes
- CSLib, `Cslib.MachineLearning.PACLearning.versionSpace_append`
- 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_append← Cslib.MachineLearning.PACLearning.versionSpace_append (Cslib/MachineLearning/PACLearning/VersionSpaceLattice.lean:51): verbatim
- Verified
- 08 Oct 2026
- Axioms
Quot.soundpropext- 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.inter_mem_versionSpacesThe version-space family is closed under intersection (append the witnessing samples).
Lean source view module on GitHub
Choose a tactic — a marked line — to see the goals Lean had before and after it, as in Lean’s infoview. Step with ← → or j k.
set_option autoImplicit true inset_option relaxedAutoImplicit true inopen Set invariable {α : Type*} {β : Type*} in/-- *The version-space meet law.* The version space of an appended sample is the intersection of the version spaces of the two parts: constraints accumulate by intersection. -/theorem Cslib.MachineLearning.PACLearning.versionSpace_append {m n : ℕ} (C : ConceptClass α β) (S : LabeledSample α β m) (T : LabeledSample α β n) : VersionSpace C (Fin.append S T) = VersionSpace C S ∩ VersionSpace C T := by ext h constructor · intro hh refine ⟨⟨hh.1, fun i => ?_⟩, hh.1, fun i => ?_⟩ · have hi := hh.2 (Fin.castAdd n i) rwa [Fin.append_left] at hi · have hi := hh.2 (Fin.natAdd m i) rwa [Fin.append_right] at hi · rintro ⟨⟨hC, hS⟩, ⟨-, hT⟩⟩ refine ⟨hC, fun i => ?_⟩ refine Fin.addCases (fun j => ?_) (fun j => ?_) i · rw [Fin.append_left] exact hS j · rw [Fin.append_right] exact hT j