Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

p. 18 (display before (24)) — the MSE of ∑iwixi+Laplace(1/η)\sum_i w_i x_i + \mathrm{Laplace}(1/\eta)∑i​wi​xi​+Laplace(1/η) is 2/η2+∑iwi2 VAR2/\eta^2 + \sum_i w_i^2\,\mathrm{VAR}2/η2+∑i​wi2​VAR

Proved
PrivAcq.Central.mse_linear_estimator

by mikedeng1 · Oct 21, 2026 · Mathlib 0df444a (Lean v4.33.1)

laplace-mechanismlinear-estimatormean-square-errorp2o-batch-pfp2ap2o-gran-per-chapterp2o-plan-paperp2o-v1

On a probability space, let Z1,…,ZnZ_1,\dots,Z_nZ1​,…,Zn​ be identically distributed random variables with mean 000, variance VAR\mathrm{VAR}VAR and ∣Zi∣≤12|Z_i| \le \tfrac12∣Zi​∣≤21​, and let LLL be a random variable with law Laplace(1/η)\mathrm{Laplace}(1/\eta)Laplace(1/η), η>0\eta > 0η>0, such that Z1,…,Zn,LZ_1,\dots,Z_n, LZ1​,…,Zn​,L are mutually independent. Let θ∈R\theta \in \mathbb Rθ∈R, let Xi=θ+ZiX_i = \theta + Z_iXi​=θ+Zi​, and let w1,…,wnw_1,\dots,w_nw1​,…,wn​ be weights with ∑iwi=1\sum_i w_i = 1∑i​wi​=1. Then the estimator θ^=∑iwiXi+L\hat\theta = \sum_i w_i X_i + Lθ^=∑i​wi​Xi​+L has mean square error

E[(θ^−θ)2]=2η2+∑i=1nwi2 VAR.\mathbb E\big[(\hat\theta - \theta)^2\big] = \frac{2}{\eta^2} + \sum_{i=1}^n w_i^2\,\mathrm{VAR}.E[(θ^−θ)2]=η22​+i=1∑n​wi2​VAR.

This closed form is the MSE used throughout the mechanism design problem of the central setting; it is the formula mse of the model file.

Formalization Note Independence is stated for the family indexed by Option (Fin n) with none ↦ L and some i ↦ Z i; the law of LLL is the published PrivLearn.Generic.laplace (1/η) (density η2e−η∣x∣\frac{\eta}{2}e^{-\eta|x|}2η​e−η∣x∣).

Preamble
import Mathlib
import Definitions.Def_PrivLearn_Generic_Privacy
Formal statement
namespace PrivAcq.Central

open MeasureTheory ProbabilityTheory

theorem mse_linear_estimator {Ω : Type*} [MeasurableSpace Ω] (P : Measure Ω)
    [IsProbabilityMeasure P] {n : ℕ} (θ var η : ℝ) (hη : 0 < η) (w : Fin n → ℝ)
    (hsum : ∑ i, w i = 1) (Z : Fin n → Ω → ℝ) (L : Ω → ℝ)
    (hZmeas : ∀ i, Measurable (Z i)) (hLmeas : Measurable L)
    (hindep : iIndepFun (fun o : Option (Fin n) => Option.elim o L Z) P)
    (hident : ∀ i j, IdentDistrib (Z i) (Z j) P P)
    (hbdd : ∀ i ω, |Z i ω| ≤ 1 / 2)
    (hmean : ∀ i, ∫ ω, Z i ω ∂P = 0)
    (hvar : ∀ i, variance (Z i) P = var)
    (hL : P.map L = PrivLearn.Generic.laplace (1 / η)) :
    ∫ ω, (∑ i, w i * (θ + Z i ω) + L ω - θ) ^ 2 ∂P = 2 / η ^ 2 + ∑ i, (w i) ^ 2 * var := by sorry

end PrivAcq.Central
Source
Fallah, Makhdoumi, Malekian, Ozdaglar, arXiv:2201.03968v2, p. 18 (display before (24)); restated in the proof of Theorem 3, p. 44; data model p. 7
Human review
  • Endorsed by Shuze Chen · Oct 21, 2026

    Confirmed by the moderator at approval.

  • Endorsed by mikedeng1 · Oct 21, 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