Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Eq. (18) — Chernoff–Hoeffding bound for the binomial distribution

Proved
BayesProphet.MultiSec.binomial_chernoff_hoeffding

by mikedeng1 · Oct 9, 2026 · Mathlib 0df444a (Lean v4.33.1)

binomialconcentrationp2o-batch-pfp2ap2o-gran-per-chapterp2o-plan-paperp2o-v1probability

Let t∈Nt\in\mathbb Nt∈N, α∈[0,1]\alpha\in[0,1]α∈[0,1], ε≥0\varepsilon\ge 0ε≥0, and X∼Bin(t,α)X\sim\mathrm{Bin}(t,\alpha)X∼Bin(t,α), so that E[X]=tα\mathbb E[X]=t\alphaE[X]=tα. Then

P[X−E[X]≤−tε]≤e−2ε2t,P[X−E[X]≥tε]≤e−2ε2t.\mathbb P\big[X-\mathbb E[X]\le -t\varepsilon\big]\le e^{-2\varepsilon^2 t},\qquad \mathbb P\big[X-\mathbb E[X]\ge t\varepsilon\big]\le e^{-2\varepsilon^2 t}.P[X−E[X]≤−tε]≤e−2ε2t,P[X−E[X]≥tε]≤e−2ε2t.

The paper quotes this from Dubhashi–Panconesi [22, Theorem 1.1] and uses it with ε=pj/2\varepsilon=p_j/2ε=pj​/2 to bound the disagreement probabilities of the Fluid Bayes Selector.

Formalization Note The probabilities are written as sums of the binomial mass function (tk)αk(1−α)t−k\binom tk\alpha^k(1-\alpha)^{t-k}(kt​)αk(1−α)t−k over k∈{0,…,t}k\in\{0,\dots,t\}k∈{0,…,t}. The hypothesis ε≥0\varepsilon\ge0ε≥0 is implicit in the paper (the bound is false for ε<0\varepsilon<0ε<0).

Preamble
import Mathlib
Formal statement
namespace BayesProphet.MultiSec

theorem binomial_chernoff_hoeffding (t : ℕ) (α ε : ℝ) (hα₀ : 0 ≤ α) (hα₁ : α ≤ 1)
    (hε : 0 ≤ ε) :
    ∑ k ∈ (Finset.range (t + 1)).filter (fun k : ℕ => (k : ℝ) - t * α ≤ -(t * ε)),
        (t.choose k : ℝ) * α ^ k * (1 - α) ^ (t - k) ≤ Real.exp (-2 * ε ^ 2 * t) ∧
    ∑ k ∈ (Finset.range (t + 1)).filter (fun k : ℕ => t * ε ≤ (k : ℝ) - t * α),
        (t.choose k : ℝ) * α ^ k * (1 - α) ^ (t - k) ≤ Real.exp (-2 * ε ^ 2 * t) := by sorry

end BayesProphet.MultiSec
Source
Vera & Banerjee, The Bayesian Prophet: A Low-Regret Framework for Online Decision Making, SSRN 3158062 (doi:10.2139/ssrn.3158062), p. 37, Eq. (18)
Human review
  • Endorsed by Shuze Chen · Oct 10, 2026

    Confirmed by the moderator at approval.

  • Endorsed by mikedeng1 · Oct 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