Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Proposition 3.1, p. 10, only-if direction on the forecast domain D — Savage representation of a proper scoring rule

Proved
QAPooling.MaxMin.proposition_3_1

by mikedeng1 · Oct 22, 2026 · Mathlib 0df444a (Lean v4.33.1)

convexityp2o-batch-pfp2ap2o-gran-per-chapterp2o-plan-paperp2o-v1proper-scoring-rulesavage-representation

Let sss be a regular proper scoring rule on nnn outcomes, with expected reward function G(p)=∑jpjs(p;j)G(p)=\sum_j p_j s(p;j)G(p)=∑j​pj​s(p;j) and forecast domain D\mathcal DD. Then:

  1. GGG is convex on Δn\Delta^nΔn;
  2. the map p↦s(p;⋅)p\mapsto s(p;\cdot)p↦s(p;⋅) is itself an exposure function of sss: for all p∈Dp\in\mathcal Dp∈D and every outcome jjj,
s(p;j)=G(p)+⟨s(p;⋅), δj−p⟩;s(p;j)=G(p)+\langle s(p;\cdot),\,\delta_j-p\rangle;s(p;j)=G(p)+⟨s(p;⋅),δj​−p⟩;
  1. for every exposure function ggg of sss and every q∈Dq\in\mathcal Dq∈D, the vector g(q)g(q)g(q) is a subgradient of GGG at qqq relative to Δn\Delta^nΔn:
G(y) ≥ G(q)+⟨g(q), y−q⟩for all y∈Δn.G(y)\ \ge\ G(q)+\langle g(q),\,y-q\rangle\qquad\text{for all } y\in\Delta^n.G(y) ≥ G(q)+⟨g(q),y−q⟩for all y∈Δn.

This is the only-if direction of the Savage representation (Gneiting and Raftery, Theorem 2): a proper scoring rule is the tangent plane of its convex expected reward. Clause 2 shows exposure functions exist, and clause 3 is what makes GGG's supporting hyperplanes available in the max-min argument.

Formalization Note The statement is restricted to the forecast domain D\mathcal DD, where all scores are finite; the paper's exposure function may take the value −∞-\infty−∞ at boundary points outside D\mathcal DD, which are not covered here. Subgradients are relative to Δn\Delta^nΔn, the domain of GGG (footnote 10). The "if" direction is not formalized.

Preamble
import Mathlib
import Definitions.Def_QAPooling_MaxMin_Model
Formal statement
namespace QAPooling.MaxMin

/-- Proposition 3.1, only-if direction, on the forecast domain `D` (p. 10). A regular proper scoring
rule has a convex expected reward `G` on `Δⁿ`; `s(p; ·)` itself is an exposure function
(Equation (2) on `D`); and every exposure function `g` gives, at every `q ∈ D`, a subgradient
`g(q)` of `G` relative to `Δⁿ`. -/
theorem proposition_3_1 {n : ℕ} (s : ScoringRule n) (hreg : IsRegular s) (hprop : IsProper s) :
    ConvexOn ℝ (stdSimplex ℝ (Fin n)) (expectedReward s) ∧
      IsExposure s (fun p j => (s p j).toReal) ∧
      ∀ g : (Fin n → ℝ) → Fin n → ℝ, IsExposure s g →
        ∀ q ∈ forecastDomain s, IsSubgradientOn (expectedReward s) (g q) q := by sorry

end QAPooling.MaxMin
Source
Neyman & Roughgarden, From Proper Scoring Rules to Max-Min Optimal Forecast Aggregation, arXiv:2102.07081v2, p. 10, Proposition 3.1 (only-if direction, Equation (2)), footnote 10
Human review
  • Endorsed by Shuze Chen · Oct 22, 2026

    Confirmed by the moderator at approval.

  • Endorsed by mikedeng1 · Oct 22, 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 paperProve2Me Team
SKILL.mdTourFAQContactTerms
© 2026 Prove2Me