Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

§A.1, Eq. (6) — Gaussian anti-concentration: Pr[g ∈ [t, t + δ]] ≤ δ/(σ√(2π)) for g ∼ N(0, σ²)

Proved
ContinualHardness.Linear.eq_6

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

gaussianp2o-gran-per-chapterp2o-plan-paperp2o-v1probability

Let σ>0\sigma>0σ>0 and let g∼N(0,σ2)g\sim N(0,\sigma^2)g∼N(0,σ2) be a centred Gaussian with variance σ2\sigma^2σ2. For every t∈Rt\in\mathbb Rt∈R and every δ≥0\delta\ge0δ≥0,

Pr⁡[g∈[t,t+δ]] ≤ δσ2π.\Pr\big[g\in[t,t+\delta]\big]\ \le\ \frac{\delta}{\sigma\sqrt{2\pi}} .Pr[g∈[t,t+δ]] ≤ σ2π​δ​.

The bound follows from the maximum 1/(σ2π)1/(\sigma\sqrt{2\pi})1/(σ2π​) of the Gaussian density; in the soundness proof of the dictatorship test (Lemma A.7) it bounds the probability that a Gaussian approximation of rtTxtr_t^{\mathsf T}x_trtT​xt​ falls in a short interval.

Formalization Note. N(0,σ2)N(0,\sigma^2)N(0,σ2) is Mathlib's gaussianReal 0 (σ²) and the probability is the measure of the closed interval [t,t+δ][t,t+\delta][t,t+δ].

Differences from the source:

  • reading: δ, t and σ unquantified ('for g ∼ N(0, σ²)') → every σ > 0, t ∈ ℝ and δ ≥ 0; reason: the interval [t, t + δ] needs δ ≥ 0 (for δ < 0 the right side is negative), and N(0, σ²) with σ > 0 is the non-degenerate Gaussian the bound is about
Preamble
import Mathlib

open MeasureTheory ProbabilityTheory
Formal statement
namespace ContinualHardness.Linear

/-- §A.1, Eq. (6), p. 16 (Gaussian anti-concentration). For `g ∼ N(0, σ²)` with `σ > 0`, every
`t ∈ ℝ` and every `δ ≥ 0`: `Pr[g ∈ [t, t + δ]] ≤ δ/(σ√(2π))`. -/
theorem eq_6 (σ t δ : ℝ) (hσ : 0 < σ) (hδ : 0 ≤ δ) :
    (gaussianReal 0 (σ ^ 2).toNNReal (Set.Icc t (t + δ))).toReal
      ≤ δ / (σ * Real.sqrt (2 * Real.pi)) := by sorry

end ContinualHardness.Linear
Source
Saket, Intractability of Continual Learning using Parametric Models with Unlimited Replay Buffer, STOC 2027 submission (manuscript sha256 86821df1…), p. 16, §A.1, Eq. (6) (PDF p. 17)
Human review
  • Endorsed by Community (Bot) · Nov 10, 2026

    Confirmed by the moderator at approval.

  • Endorsed by Shuze Chen · 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