Lemma 5.2 — Category averaging as projection
OpenCalibratedMA.Randomized.Supplement.lemma_5_2calibrationmultiaccuracyp2o-batch-stoc27sp2o-gran-per-chapterp2o-plan-paperp2o-v1sample-complexity
Let have , let be measurable, and let be a measurable assignment to finitely many categories. With , write , and . Then all the following identities hold:
for every bounded measurable real test , and
These are all of (7), (8) and (9), supporting Theorem 5.1. Empty categories contribute zero.
Differences from the source:
- encoding: labels in [0,1] or in {0,1} → real labels with the corresponding almost-sure support predicate; reason: the measures are the same labeled laws
- encoding: finite categories and a bounded test → Fin r categories, Boolean signs, and a measurable real test with an existential uniform bound; reason: finite relabeling and the ordinary measurability convention preserve all expectations
- encoding: conditional projection identities → context marginal D.map Prod.fst, explicit category integrals and almost-everywhere conditional equality; reason: the displayed conditional identities are version-independent; zero-mass categories contribute zero
Preamble
import Mathlib import Definitions.Def_CalibratedMA_Randomized_Supplement_Categories open MeasureTheory
Formal statement
namespace CalibratedMA.Randomized.Supplement
/-- Lemma 5.2, pp.21–22: all identities (7), (8), (9). -/
theorem lemma_5_2 (X : Type) [MeasurableSpace X] (D : Measure (X × ℝ))
(hD : IsLabeledDist D) (S : X → ℝ) (hS : IsDetPredictor S)
(r : ℕ) (J : X → Fin r) (hJ : Measurable J) :
let P := D.map Prod.fst
let R := categoryResidual P S J
(P[R | MeasurableSpace.comap J inferInstance] =ᵐ[P] 0) ∧
(∫ x, S x * R x ∂P) = (∫ x, R x ^ 2 ∂P) ∧
(∀ g : X → ℝ, Measurable g → (∃ M : ℝ, ∀ x, |g x| ≤ M) →
(∫ x, g x * R x ∂P) =
∑ j : Fin r, (P {x | J x = j}).toReal * categoryCovariance P S g J j) ∧
cellCalibration D (categoryPredictor P S J) J = categorySignMaximum D S J := by sorry
end CalibratedMA.Randomized.Supplement
Source
Jiuyao Lu, Georgy Noarov, Aaron Roth, Calibrated Multiaccuracy: Deterministic and Randomized Sample Complexity, STOC 2027 submission #900 (October 2026; title page November 2, 2026), p. 21-22, Lemma 5.2 (PDF pp. 23-24)