Cslib.MachineLearning.PACLearning.pi_map_graph_eq_one
theoremverifiedformalizationimported Lean
The iid product of the realizable joint distribution assigns measure 1 to the set of samples where every coordinate lies on the graph of c.
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 lemma Cslib.MachineLearning.PACLearning.pi_map_graph_eq_one [MeasurableSpace α] [MeasurableSpace β] {c : α → β} (hcm : Measurable c) (P : Measure α) [IsProbabilityMeasure P] (hG : MeasurableSet {p : α × β | p.2 = c p.1}) {m : ℕ} : (Measure.pi (fun _ : Fin m => P.map (fun x => (x, c x)))) (Set.univ.pi (fun _ : Fin m => {p : α × β | p.2 = c p.1})) = 1
- Formalizes
- CSLib, `Cslib.MachineLearning.PACLearning.pi_map_graph_eq_one`
- 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.pi_map_graph_eq_one← Cslib.MachineLearning.PACLearning.pi_map_graph_eq_one (Cslib/MachineLearning/PACLearning/VersionSpace.lean:248): verbatim
- Verified
- 08 Oct 2026
- Axioms
Classical.choiceQuot.soundpropext- Built on 1
- Cslib.MachineLearning.PACLearning.map_graph_eq_oneUnder the pushforward of a probability measure
Palong the graph mapx ↦ (x, c x), the graph ofchas measure1.
- Cslib.MachineLearning.PACLearning.map_graph_eq_oneUnder the pushforward of a probability measure
- Used by 1
- Cslib.MachineLearning.PACLearning.ae_mem_versionSpace_of_realizableUnder iid sampling from the realizable joint distribution induced by
c ∈ Cand a probability measurePonα, the target conceptc…
- Cslib.MachineLearning.PACLearning.ae_mem_versionSpace_of_realizableUnder iid sampling from the realizable joint distribution induced by
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 MeasureTheory Set inopen scoped ENNReal invariable {α : Type*} {β : Type*} in/-- The iid product of the realizable joint distribution assigns measure `1` to the set of samples where every coordinate lies on the graph of `c`. -/lemma Cslib.MachineLearning.PACLearning.pi_map_graph_eq_one [MeasurableSpace α] [MeasurableSpace β] {c : α → β} (hcm : Measurable c) (P : Measure α) [IsProbabilityMeasure P] (hG : MeasurableSet {p : α × β | p.2 = c p.1}) {m : ℕ} : (Measure.pi (fun _ : Fin m => P.map (fun x => (x, c x)))) (Set.univ.pi (fun _ : Fin m => {p : α × β | p.2 = c p.1})) = 1 := by have hφ : Measurable (fun x : α => (x, c x)) := by fun_prop have : IsProbabilityMeasure (P.map (fun x : α => (x, c x))) := Measure.isProbabilityMeasure_map hφ.aemeasurable rw [Measure.pi_pi] simp [map_graph_eq_one hcm P hG]