Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Proof of Theorem 5.16(2), p. 30 — Σ_{(r,a)} 2⟨f⁰_g, c⁰_{r,a}⟩² ≤ 1

Proved
PrivLearn.MaskedParity.bessel

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

fourier-analysisp2o-batch-pfp2bp2o-gran-per-chapterp2o-plan-paperp2o-v1paritystatistical-query-learning

Let ddd be a power of two, let examples be uniform on the MASKED-PARITY domain DDD, and let ggg be a statistical query with values in {+1,−1}\{+1,-1\}{+1,−1} on labels y∈{+1,−1}y\in\{+1,-1\}y∈{+1,−1}. Then

∑(r,a)∈{0,1}d×{0,1}2⋅⟨fg0,cr,a0⟩2≤1.\sum_{(r,a)\in\{0,1\}^d\times\{0,1\}}2\cdot\langle f^0_g,c^0_{r,a}\rangle^2\le1 .(r,a)∈{0,1}d×{0,1}∑​2⋅⟨fg0​,cr,a0​⟩2≤1.

This Bessel inequality bounds the total correlation of one query with all the b=0b=0b=0 halves of the concepts, which is what limits how many targets a single nonadaptive query can distinguish.

Formalization Note. The range condition on ggg is the paper's (g:{0,1}d×{0,1}log⁡d×{0,1}×{+1,−1}→{+1,−1}g:\{0,1\}^d\times\{0,1\}^{\log d}\times\{0,1\}\times\{+1,-1\}\to\{+1,-1\}g:{0,1}d×{0,1}logd×{0,1}×{+1,−1}→{+1,−1}, p. 29); values of ggg at other labels play no role.

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

/-- **Bessel display** (p. 30). Let `d` be a power of two and let `g` be a statistical query
with values `±1` on labels `±1`. Then
`∑_{(r,a) ∈ {0,1}^d × {0,1}} 2 · ⟨f^0_g, c^0_{r,a}⟩² ≤ 1`. -/
theorem bessel {d : ℕ} (hd : ∃ m : ℕ, d = 2 ^ m) (g : Dom d → ℝ → ℝ)
    (hg : ∀ u y, (y = 1 ∨ y = -1) → (g u y = 1 ∨ g u y = -1)) :
    ∑ ra : (Fin d → ZMod 2) × ZMod 2, 2 * ip (half 0 (fg g)) (half 0 (cMP ra.1 ra.2)) ^ 2 ≤ 1 := by sorry

end PrivLearn.MaskedParity
Source
Kasiviswanathan, Lee, Nissim, Raskhodnikova and Smith, What Can We Learn Privately?, arXiv:0803.0924v3, p. 30, proof of Theorem 5.16 part (2), display 'Summing the two previous equations'
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