Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Theorem 9.2 (Chernoff bounds): additive and multiplicative tail bounds for m independent Bernoulli trials

Proved
ComputationalLearning.chernoff_bounds

by naimengye · Sep 24, 2026 · Mathlib 0df444a (Lean v4.33.1)

chernoff-boundsconcentrationprobability

Theorem 9.2. Let X1,…,XmX_1, \dots, X_mX1​,…,Xm​ be a sequence of mmm independent Bernoulli trials, each with probability of success E[Xi]=pE[X_i] = pE[Xi​]=p. Let S=X1+⋯+XmS = X_1 + \dots + X_mS=X1​+⋯+Xm​, so E[S]=pmE[S] = pmE[S]=pm. Then for 0<γ≤10 < \gamma \le 10<γ≤1: (additive form) Pr⁡[S>(p+γ)m]≤e−2mγ2\Pr[S > (p+\gamma)m] \le e^{-2m\gamma^2}Pr[S>(p+γ)m]≤e−2mγ2 and Pr⁡[S<(p−γ)m]≤e−2mγ2\Pr[S < (p-\gamma)m] \le e^{-2m\gamma^2}Pr[S<(p−γ)m]≤e−2mγ2; (multiplicative form) Pr⁡[S>(1+γ)pm]≤e−mpγ2/3\Pr[S > (1+\gamma)pm] \le e^{-mp\gamma^2/3}Pr[S>(1+γ)pm]≤e−mpγ2/3 and Pr⁡[S<(1−γ)pm]≤e−mpγ2/2\Pr[S < (1-\gamma)pm] \le e^{-mp\gamma^2/2}Pr[S<(1−γ)pm]≤e−mpγ2/2.

Formally, on the product law of mmm Bernoulli(ppp) trials, 0≤p≤10 \le p \le 10≤p≤1, the four bounds with non-strict inequalities in the events (stronger than the printed strict ones).

Preamble
import Definitions.Def_ComputationalLearning_Boosting

open MeasureTheory ProbabilityTheory
Formal statement
namespace ComputationalLearning

/-- **Theorem 9.2 (Chernoff bounds)** (p. 190). Let `X₁, …, Xₘ` be independent Bernoulli trials
with success probability `p` and `S = X₁ + ⋯ + Xₘ`, so `E[S] = pm`. Then for `0 < γ ≤ 1`:
(additive form) `Pr[S ≥ (p + γ)m] ≤ e^{−2mγ²}` and `Pr[S ≤ (p − γ)m] ≤ e^{−2mγ²}`;
(multiplicative form) `Pr[S ≥ (1 + γ)pm] ≤ e^{−mpγ²/3}` and `Pr[S ≤ (1 − γ)pm] ≤ e^{−mpγ²/2}`. -/
theorem chernoff_bounds {p : ℝ} (hp0 : 0 ≤ p) (hp1 : p ≤ 1) (m : ℕ) {γ : ℝ} (hγ : 0 < γ)
    (hγ1 : γ ≤ 1) :
    trialsLaw p m {ω | (p + γ) * m ≤ successes ω} ≤ ENNReal.ofReal (Real.exp (-(2 * m * γ ^ 2))) ∧
    trialsLaw p m {ω | (successes ω : ℝ) ≤ (p - γ) * m} ≤
      ENNReal.ofReal (Real.exp (-(2 * m * γ ^ 2))) ∧
    trialsLaw p m {ω | (1 + γ) * p * m ≤ successes ω} ≤
      ENNReal.ofReal (Real.exp (-(m * p * γ ^ 2 / 3))) ∧
    trialsLaw p m {ω | (successes ω : ℝ) ≤ (1 - γ) * p * m} ≤
      ENNReal.ofReal (Real.exp (-(m * p * γ ^ 2 / 2))) := by sorry

end ComputationalLearning
Source
Kearns and Vazirani, An Introduction to Computational Learning Theory, MIT Press 1994, doi:10.7551/mitpress/3897.001.0001, Chapter 9, §9.3 p. 190, Theorem 9.2
Human review
  • Endorsed by Shuze Chen · Sep 25, 2026

    Confirmed by the moderator at approval.

  • Endorsed by naimengye · Sep 25, 2026

    Confirmed by the mission captain (proposal self-audit).

  • 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