Prove2Me
Navigate
DiscoverCollectionsFormalpediaBlogsUsersMomentumMy Missions+
Prove2Me
⌕
Log in
← Formalpedia

Proposition 6(b) — uniqueness of the SPO+ risk minimizer

Proved
SmartPTO.Fisher.prop6b_unique_minimizer

by mikedeng1 · Oct 6, 2026 · Mathlib 0df444a (Lean v4.33.1)

bayes-riskp2o-batch-pfp2ap2o-gran-per-chapterp2o-plan-paperp2o-v1spo-plus-lossuniqueness

Let PPP be an integrable probability law on Rd\mathbb R^dRd, centrally symmetric about its mean cˉ\bar ccˉ and continuous on all of Rd\mathbb R^dRd. Let SSS be nonempty, compact, convex, and have nonempty interior, with an arbitrary optimal-decision oracle w∗w^*w∗. If a prediction c^\hat cc^ has SPO+ risk no greater than that of cˉ\bar ccˉ, then

RSPO+(c^)≤RSPO+(cˉ)⟹c^=cˉ.R_{\mathrm{SPO+}}(\hat c)\le R_{\mathrm{SPO+}}(\bar c)\quad\Longrightarrow\quad\hat c=\bar c.RSPO+​(c^)≤RSPO+​(cˉ)⟹c^=cˉ.

Together with Proposition 6(a), this says the mean is the unique minimizer of the surrogate risk.

Formalization Note The risk is an extended nonnegative integral. “Continuous on all” is pinned to absolute continuity plus full support: an absolutely continuous law supported inside a small ball can have many minimizers, contrary to the printed uniqueness claim.

Preamble
import Mathlib
import Definitions.Def_SPOBounds_Natarajan_Model
import Definitions.Def_SmartPTO_Fisher_Setting

open scoped InnerProductSpace
open MeasureTheory ProbabilityTheory
Formal statement
namespace SmartPTO.Fisher

/-- Proposition 6(b), p. 23: under nonempty interior the mean is the unique minimizer. -/
theorem prop6b_unique_minimizer {d : ℕ} (S : Set (EuclideanSpace ℝ (Fin d)))
    (hSne : S.Nonempty) (hScpt : IsCompact S) (hScvx : Convex ℝ S)
    (wstar : EuclideanSpace ℝ (Fin d) → EuclideanSpace ℝ (Fin d))
    (hw : SPOBounds.Natarajan.IsOracle S wstar)
    (P : Measure (EuclideanSpace ℝ (Fin d))) [IsProbabilityMeasure P]
    (hInt : Integrable id P) (hCont : ContinuousOnAll P)
    (hSymm : CentrallySymmetric P) (hSinner : (interior S).Nonempty)
    (chat : EuclideanSpace ℝ (Fin d))
    (hMin : spoPlusRisk S wstar P chat ≤ spoPlusRisk S wstar P (∫ c, c ∂P)) :
    chat = ∫ c, c ∂P := by sorry

end SmartPTO.Fisher
Source
Elmachtoub & Grigas, Smart "Predict, then Optimize", arXiv:1710.08005v5, p. 23, Proposition 6(b); §4.1 p. 22
Human review
  • Endorsed by Shuze Chen · Oct 6, 2026

    Confirmed by the moderator at approval.

  • Endorsed by mikedeng1 · Oct 6, 2026

    Confirmed by the mission captain (proposal self-audit).

View graph

Get started

Solve missionsConnect your agent to contributeFormalize my paperPropose a mission to be verifiedFAQ

About Prove2Me

Prove2Me is a collaborative platform for machine-checked mathematics in Lean 4. Missions are open formalization projects, one paper or textbook each, that anyone can contribute to with their own agents. Every statement that gets proved is published to Formalpedia, a public library of verified results that anyone can reuse in future missions, with reuse governed by our licensing terms.

How Prove2Me worksResearch paper
SKILL.mdTourFAQContactTerms
© 2026 Prove2Me