Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Equation (7) — E[g(u, c_{r,a}(u))] = C_g + ⟨f⁰_g, c⁰_{r,a}⟩ + ⟨f¹_g, c¹_{r,a}⟩

Proved
PrivLearn.MaskedParity.eq_7

by mikedeng1 · Oct 7, 2026 · Mathlib 0df444a (Lean v4.33.1)

fourier-analysislearning-theoryp2o-batch-pfp2bp2o-gran-per-chapterp2o-plan-paperp2o-v1statistical-query-learning

Let examples be uniform on the MASKED-PARITY domain DDD. For every statistical query g(u,y)g(u,y)g(u,y) with real values and every target cr,ac_{r,a}cr,a​,

E[g(x,i,b,cr,a(x,i,b))]=Cg+⟨fg0,cr,a0⟩+⟨fg1,cr,a1⟩.\mathbb E\bigl[g(x,i,b,c_{r,a}(x,i,b))\bigr]=C_g+\langle f^0_g,c^0_{r,a}\rangle+\langle f^1_g,c^1_{r,a}\rangle .E[g(x,i,b,cr,a​(x,i,b))]=Cg​+⟨fg0​,cr,a0​⟩+⟨fg1​,cr,a1​⟩.

The true answer to a query splits into a part independent of the target, a part that depends only on rrr (the half b=1b=1b=1), and the only part that depends on the mask bit aaa (the half b=0b=0b=0).

Formalization Note. The identity holds for every real-valued ggg because the labels are ±1\pm1±1. The statement imposes no condition on ddd.

Preamble
import Mathlib
import Definitions.Def_PrivLearn_MaskedParity_Model
import Definitions.Def_PrivLearn_MaskedParity_Oracle
Formal statement
namespace PrivLearn.MaskedParity

/-- **Equation (7)** (p. 29). For every real-valued query `g(u, y)` and every target `c_{r,a}`,
`E[g(u, c_{r,a}(u))] = C_g + ⟨f^0_g, c^0_{r,a}⟩ + ⟨f^1_g, c^1_{r,a}⟩`. -/
theorem eq_7 {d : ℕ} (r : Fin d → ZMod 2) (a : ZMod 2) (g : Dom d → ℝ → ℝ) :
    qval (cMP r a) g =
      Cg g + ip (half 0 (fg g)) (half 0 (cMP r a)) + ip (half 1 (fg g)) (half 1 (cMP r a)) := by sorry

end PrivLearn.MaskedParity
Source
Kasiviswanathan, Lee, Nissim, Raskhodnikova and Smith, What Can We Learn Privately?, arXiv:0803.0924v3, p. 29, equation (7)
Human review
  • Endorsed by Shuze Chen · Oct 7, 2026

    Confirmed by the moderator at approval.

  • Endorsed by mikedeng1 · Oct 7, 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