Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

§2.2, p. 4 — under Assumption A, P{|ĝ_N(x) − g(x)| ≥ α(ε)/2} ≤ e^{−Nγ_x} + e^{−Nγ′_x}

Proved
KleywegtSAA.ExpRate.deviation_le_two_exp

by mikedeng1 · Oct 7, 2026 · Mathlib 0df444a (Lean v4.33.1)

large-deviationsp2o-batch-pfp2ap2o-gran-per-chapterp2o-plan-paperp2o-v1sample-average-approximation

Assume the standing setting of §1–§2 and Assumption A. Let r>0r > 0r>0. Then for every x∈Sx \in \mathcal Sx∈S there are constants γx>0\gamma_x > 0γx​>0 and γx′>0\gamma'_x > 0γx′​>0 such that for every sample size N≥1N \ge 1N≥1,

P{∣g^N(x)−g(x)∣≥r}≤e−Nγx+e−Nγx′.P\big\{ |\hat g_N(x) - g(x)| \ge r \big\} \le e^{-N\gamma_x} + e^{-N\gamma'_x}.P{∣g^​N​(x)−g(x)∣≥r}≤e−Nγx​+e−Nγx′​.

On the page r=α(ε)/2r = \alpha(\varepsilon)/2r=α(ε)/2, and γx,γx′\gamma_x, \gamma'_xγx​,γx′​ are the values of the rate functions of G(x,W)G(x,W)G(x,W) and −G(x,W)-G(x,W)−G(x,W) at g(x)+rg(x) + rg(x)+r and −g(x)+r-g(x) + r−g(x)+r. Taking γ=min⁡x∈S{γx,γx′}\gamma = \min_{x \in \mathcal S}\{\gamma_x, \gamma'_x\}γ=minx∈S​{γx​,γx′​} and summing over S\mathcal SS in the union bound yields Proposition 2.2.

Formalization Note The standing setting of §1–§2 is carried as hypotheses: S\mathcal SS is a nonempty finite set of an arbitrary type, each G(x,⋅)G(x,\cdot)G(x,⋅) is measurable, the sample W1,W2,…W^1, W^2, \dotsW1,W2,… is an independent, identically distributed sequence of measurable maps on a probability space (Ω,P)(\Omega, P)(Ω,P) (the paper's WnW^nWn is the (n−1)(n-1)(n−1)-st term of a 000-indexed sequence, and the law of WWW is that of the first term), and E∣G(x,W)∣<∞E|G(x,W)| < \inftyE∣G(x,W)∣<∞ for every x∈Sx \in \mathcal Sx∈S. The statement is made for every r>0r > 0r>0 rather than only for r=α(ε)/2r = \alpha(\varepsilon)/2r=α(ε)/2; this is stronger and avoids the nonemptiness of S∖Sε\mathcal S \setminus \mathcal S^\varepsilonS∖Sε. The constants are real numbers: when a rate function is +∞+\infty+∞, any positive constant works.

Preamble
import Mathlib
import Definitions.Def_KleywegtSAA_ExpRate_Setting

open MeasureTheory ProbabilityTheory Filter Topology
Formal statement
namespace KleywegtSAA.ExpRate

/-- §2.2, p. 4: under Assumption A, for every `r > 0` (the page's `r = α(ε)/2`) and every
`x ∈ S` there are `γ_x, γ'_x > 0` with `P{|ĝ_N(x) − g(x)| ≥ r} ≤ e^{−Nγ_x} + e^{−Nγ'_x}` for all
`N ≥ 1`. -/
theorem deviation_le_two_exp
    {X : Type*} (S : Finset X) (hS : S.Nonempty)
    {𝒲 : Type*} [MeasurableSpace 𝒲] (G : X → 𝒲 → ℝ) (hG : ∀ x ∈ S, Measurable (G x))
    {Ω : Type*} [MeasurableSpace Ω] (P : Measure Ω) [IsProbabilityMeasure P]
    (W : ℕ → Ω → 𝒲) (hWm : ∀ n, Measurable (W n)) (hind : iIndepFun W P)
    (hid : ∀ n, IdentDistrib (W n) (W 0) P P)
    (hint : ∀ x ∈ S, Integrable (fun ω => G x (W 0 ω)) P)
    (hA : AssumptionA S G P W) (r : ℝ) (hr : 0 < r) :
    ∀ x ∈ S, ∃ γx γx' : ℝ, 0 < γx ∧ 0 < γx' ∧ ∀ N : ℕ, 1 ≤ N →
      P {ω | r ≤ |sampleObj G W N ω x - trueObj G P W x|} ≤
        ENNReal.ofReal (Real.exp (-((N : ℝ) * γx)) + Real.exp (-((N : ℝ) * γx'))) := by sorry

end KleywegtSAA.ExpRate
Source
Kleywegt & Shapiro, The sample average approximation method for stochastic discrete optimization, preprint (two-author version, sha256 56657748…), p. 4, §2.2, after Assumption A
Human review
  • Endorsed by Shuze Chen · Oct 7, 2026

    Confirmed by the moderator at approval.

  • 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