Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Lemma 3 — group privacy with the exact additive term

Proved
PrivPACLower.ICP.lemma_3

by mikedeng1 · Nov 10, 2026 · Mathlib 0df444a (Lean v4.33.1)

differential-privacymachine-learningp2o-batch-stoc27ap2o-gran-per-chapterp2o-plan-paperp2o-v1probability

Let MMM be an (ε,δ)(\varepsilon,\delta)(ε,δ)-DP mechanism on nnn records, with ε>0\varepsilon>0ε>0 and 0≤δ<10\le\delta<10≤δ<1. If databases S,S′S,S'S,S′ differ in exactly rrr records, every measurable output event EEE satisfies

Pr⁡[M(S)∈E]≤erεPr⁡[M(S′)∈E]+δ∑s=0r−1esε.\Pr[M(S)\in E]\le e^{r\varepsilon}\Pr[M(S')\in E]+\delta\sum_{s=0}^{r-1}e^{s\varepsilon}.Pr[M(S)∈E]≤erεPr[M(S′)∈E]+δs=0∑r−1​esε.

For databases differing in at most rrr records, the same comparison holds with additive term re(r−1)εδr e^{(r-1)\varepsilon}\deltare(r−1)εδ. The case r=0r=0r=0 includes identical databases and an empty sum. These comparisons provide the privacy guarantee for repetition and the two-point learner lower bound.

Differences from the source:

  • encoding: binary hypotheses, ordered databases and ordinary probabilities → Bool hypotheses, Fin-indexed databases, probability measures and extended nonnegative error probabilities; reason: retains replacement adjacency, improper outputs and the joint sample-and-learner experiment; all applied thresholds are nonnegative
Preamble
import Mathlib
import Definitions.Def_PrivateUniformGen_Characterization_Privacy
import Definitions.Def_PrivPACLower_ICP_Reductions
open MeasureTheory ProbabilityTheory
open scoped BigOperators ENNReal
set_option autoImplicit false
Formal statement
namespace PrivPACLower.ICP

open PrivateUniformGen.Characterization


theorem lemma_3 {Z O : Type*} [MeasurableSpace O] {n : ℕ}
    (ε δ : ℝ) (hε : 0 < ε) (hδ : 0 ≤ δ ∧ δ < 1)
    (M : Mechanism Z O n) (hM : IsDP M ε δ) :
    (∀ (S S' : Fin n → Z) (r : ℕ), hamming S S' = r →
      ∀ E : Set O, MeasurableSet E →
        (M S : Measure O).real E ≤ Real.exp ((r : ℝ)*ε) * (M S' : Measure O).real E +
          δ * ∑ s ∈ Finset.range r, Real.exp ((s : ℝ)*ε)) ∧
    (∀ (r : ℕ) (S S' : Fin n → Z), hamming S S' ≤ r →
      ∀ E : Set O, MeasurableSet E →
        (M S : Measure O).real E ≤ Real.exp ((r : ℝ)*ε) * (M S' : Measure O).real E +
          (r : ℝ) * Real.exp (((r : ℝ)-1)*ε) * δ) := by sorry

end PrivPACLower.ICP
Source
Prathamesh Dharangutte, Amartya Sanyal, STOC 2027 submission #366 (October 2026), p. 11, Lemma 3. https://github.com/sigact-stoc/stoc2027/releases/download/papers-1/366.pdf
Human review
  • Endorsed by Shuze Chen · Nov 10, 2026

    Confirmed by the moderator at approval.

  • Endorsed by mikedeng1 · Nov 10, 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