Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Theorem 1, p. 9 — if every conditional outcome function is ϵ-smooth, the DN estimator's bias is at most d²ϵ

Proved
DiffNeighbors.Bias.theorem_1

by mikedeng1 · Oct 23, 2026 · Mathlib 0df444a (Lean v4.33.1)

differences-in-neighborsestimator-biasnetwork-interferencep2o-batch-pfp2ap2o-gran-per-chapterp2o-plan-paperp2o-v1

Consider NNN units with an undirected interference graph GGG without self-loops, maximum degree d=max⁡i∣Ni∣d = \max_i |\mathcal N_i|d=maxi​∣Ni​∣, and potential outcome functions fi:{0,1}N→Rf_i : \{0,1\}^N \to \mathbb Rfi​:{0,1}N→R satisfying Assumption 1 (neighborhood interference: fi(z)f_i(z)fi​(z) depends only on ziz_izi​ and (zj)j∈Ni(z_j)_{j \in \mathcal N_i}(zj​)j∈Ni​​). Treatments are assigned by the Bernoulli design, ziz_izi​ i.i.d. Bernoulli(p)(p)(p) with 0<p<10 < p < 10<p<1. Let

ATE=1N∑i=1N(fi(1⃗)−fi(0⃗))\mathrm{ATE} = \frac1N \sum_{i=1}^N \bigl(f_i(\vec 1) - f_i(\vec 0)\bigr)ATE=N1​i=1∑N​(fi​(1)−fi​(0))

and let ATEDN\mathrm{ATE}_{\mathrm{DN}}ATEDN​ be the Differences-in-Neighbors estimator (3). Suppose that the conditional outcome functions fi1f^1_ifi1​ and fi0f^0_ifi0​ are ϵ\epsilonϵ-smooth for all nodes iii, i.e. ∣Δjkfia(z)∣≤ϵ|\Delta_{jk} f^a_i(z)| \le \epsilon∣Δjk​fia​(z)∣≤ϵ for all aaa, zzz, jjj, kkk. Then

∣ATE−E[ATEDN]∣≤d2ϵ.\bigl|\mathrm{ATE} - \mathbb E[\mathrm{ATE}_{\mathrm{DN}}]\bigr| \le d^2 \epsilon.​ATE−E[ATEDN​]​≤d2ϵ.

The bound is second order in the strength of interference: under the paper's outcome model with interference magnitude δ\deltaδ it gives bias O(d2δ2)O(d^2\delta^2)O(d2δ2) (Corollary 1), against first order Θ(dδ)\Theta(d\delta)Θ(dδ) for the difference-in-means estimator, while the DN estimator's variance stays polynomial in ddd.

Differences from the source:

  • encoding: units [N] = {1,…,N}, treatment vectors z ∈ {0,1}^N, an undirected graph without self-loops, d = max_i |N_i| → a finite type ι with N = card ι, z : ι → Bool with 1/0 read through ind, G : SimpleGraph ι, N_i = G.neighborFinset i, d = G.maxDegree; reason: a simple graph is exactly an undirected graph without self-loops; same instances
  • encoding: E[·] over z_i i.i.d. Bernoulli(p) → bernExp p h = Σ_z (Π_j (p if z_j = 1 else 1 − p)) h(z), a finite sum; reason: the law of the design on the finite set {0,1}^N; same values
  • encoding: a Bernoulli(p) design whose weights divide by p and 1 − p → hypotheses 0 < p and p < 1; reason: the weights 1/p and 1/(1 − p) and the design presuppose p ∈ (0,1); this only excludes undefined cases
  • encoding: Assumption 1, stated "throughout this work" (p. 5) → an explicit hypothesis hf : NeighborhoodInterference G f; reason: a standing assumption of the paper made explicit; Theorem 1 is false without it
  • encoding: f^a_i as a function of z_{N_i}; E[f^a(Z) | Z_j = b] and E[f^a(Z) | Z_j = b, Z_k = c] → condOutcome f i a z = f_i(z with z_i := a), a function on all of {0,1}^N; conditional expectations are bernExp of the function with the conditioned coordinates overwritten by Function.update; reason: under Assumption 1 condOutcome f i a depends only on z_{N_i}; by independence of the coordinates, conditioning on Z_j = b is the same as setting z_j := b
Preamble
import Mathlib
import Definitions.Def_DiffNeighbors_Bias_Model
Formal statement
namespace DiffNeighbors.Bias

open Finset

/-- **Theorem 1** (Peng–Ye–Zheng, arXiv:2503.02271v1, p. 9). Under neighborhood interference
(Assumption 1, standing throughout the paper) and the Bernoulli(`p`) design, if every conditional
outcome function `f^1_i`, `f^0_i` is `ε`-smooth, then the bias of the DN estimator is at most `d²ε`,
where `d = max_i |N_i|` is the maximum degree of the interference graph. -/
theorem theorem_1 {ι : Type*} [Fintype ι] [DecidableEq ι] (G : SimpleGraph ι) [DecidableRel G.Adj]
    (f : ι → (ι → Bool) → ℝ) (hf : NeighborhoodInterference G f)
    (p ε : ℝ) (hp0 : 0 < p) (hp1 : p < 1)
    (hε : ∀ i, ∀ a : Bool, IsSmooth ε (condOutcome f i a)) :
    |ate f - bernExp p (dnEstimator G p f)| ≤ (G.maxDegree : ℝ) ^ 2 * ε := by sorry

end DiffNeighbors.Bias
Source
Peng, Ye, Zheng, Differences-in-Neighbors for Network Interference in Experiments, arXiv:2503.02271v1, p. 9, Theorem 1 (with §2.1, Assumption 1, p. 5; (3), p. 7; ϵ-smoothness, p. 9)
Human review
  • Endorsed by Shuze Chen · Oct 23, 2026

    Confirmed by the moderator at approval.

  • Endorsed by mikedeng1 · Oct 23, 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