Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Lemma 17 — directional derivative of an optimal value

Proved
GenEmpLik.Coverage.lemma_17

by mikedeng1 · Oct 6, 2026 · Mathlib 0df444a (Lean v4.33.1)

hadamard-differentiabilityoptimal-valuep2o-batch-pfp2bp2o-gran-per-chapterp2o-plan-paperp2o-v1

Let FFF be a lower semicontinuous real objective on a nonempty closed decision set X\mathcal XX. Suppose some nonempty near-minimizer set {x∈X:F(x)≤inf⁡XF+ε0}\{x\in\mathcal X:F(x)\le\inf_{\mathcal X}F+\varepsilon_0\}{x∈X:F(x)≤infX​F+ε0​} is compact. Let HHH be continuous and bounded on X\mathcal XX, let each HnH_nHn​ be bounded there, and suppose sup⁡x∈X∣Hn(x)−H(x)∣→0\sup_{x\in\mathcal X}|H_n(x)-H(x)|\to0supx∈X​∣Hn​(x)−H(x)∣→0. For positive tn→0t_n\to0tn​→0, writing S⋆=arg⁡min⁡XFS^\star=\arg\min_{\mathcal X}FS⋆=argminX​F, one has

inf⁡x∈X{F(x)+tnHn(x)}−inf⁡x∈XFtn⟶inf⁡x∈S⋆H(x).\frac{\inf_{x\in\mathcal X}\{F(x)+t_nH_n(x)\}-\inf_{x\in\mathcal X}F}{t_n}\longrightarrow\inf_{x\in S^\star}H(x).tn​infx∈X​{F(x)+tn​Hn​(x)}−infx∈X​F​⟶x∈S⋆inf​H(x).

This is the optimal-value directional derivative used to identify the influence function.

Formalization Note Signed measures are represented by their action H(x)=∫ℓ(x;z) dH(z)H(x)=\int\ell(x;z)\,dH(z)H(x)=∫ℓ(x;z)dH(z) on the loss class. Positive tnt_ntn​ follows the directional reading used in Appendix C.2.

Preamble
import Mathlib

open Filter Topology
Formal statement
namespace GenEmpLik.Coverage

/-- Lemma 17, pp. 38–40, in the action of signed measures on the loss class. -/
theorem lemma_17 {E : Type*} [MetricSpace E]
    (X : Set E) (F H : E → ℝ) (Hn : ℕ → E → ℝ) (t : ℕ → ℝ)
    (hXclosed : IsClosed X) (hXnonempty : X.Nonempty)
    (hFlsc : LowerSemicontinuousOn F X)
    (hsublevel : ∃ ε₀ : ℝ, 0 < ε₀ ∧
      IsCompact {x | x ∈ X ∧ F x ≤ sInf (F '' X) + ε₀} ∧
      Set.Nonempty {x | x ∈ X ∧ F x ≤ sInf (F '' X) + ε₀})
    (hHcont : ContinuousOn H X)
    (hHbdd : BddAbove ((fun x => |H x|) '' X))
    (hHnbdd : ∀ n, BddAbove ((fun x => |Hn n x|) '' X))
    (htpos : ∀ n, 0 < t n) (htzero : Tendsto t atTop (𝓝 0))
    (hHn : Tendsto (fun n => ⨆ x : X, |Hn n x - H x|) atTop (𝓝 0)) :
    Tendsto (fun n =>
      (sInf ((fun x => F x + t n * Hn n x) '' X) - sInf (F '' X)) / t n)
      atTop (𝓝 (sInf (H '' {x | x ∈ X ∧ F x = sInf (F '' X)}))) := by sorry

end GenEmpLik.Coverage
Source
Duchi, Glynn & Namkoong, Statistics of Robust Optimization: A Generalized Empirical Likelihood Approach, arXiv:1610.03425v3, p. 38, Lemma 17; proof pp. 39–40
Human review
  • Endorsed by Shuze Chen · Oct 6, 2026

    Confirmed by the moderator at approval.

  • Endorsed by mikedeng1 · Oct 6, 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