Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Theorem 4.1 — ε-accuracy for D-optimal design

Proved
RelSmoothFOM.DOptimal.theorem_4_1

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

d-optimal-designfirst-order-methodslog-barrierp2o-batch-pfp2ap2o-gran-per-chapterp2o-plan-paperp2o-v1relative-smoothness

Let H∈Rm×nH\in\mathbb R^{m\times n}H∈Rm×n have rank mmm, with n≥m+1n\ge m+1n≥m+1. Run the primal gradient scheme on the positive simplex for f(x)=−log⁡det⁡(HDiag⁡(x)H⊤)f(x)=-\log\det(H\operatorname{Diag}(x)H^\top)f(x)=−logdet(HDiag(x)H⊤), using the log barrier, relative-smoothness constant 111, and x0=e/nx^0=e/nx0=e/n. Let x∗x^*x∗ attain the minimum among feasible simplex points where the information matrix is positive definite, and write f∗=f(x∗)f^*=f(x^*)f∗=f(x∗). If 0<ε≤f(x0)−f∗0<\varepsilon\le f(x^0)-f^*0<ε≤f(x0)−f∗ and

k≥2nlog⁡ ⁣(2(f(x0)−f∗)/ε)ε,k\ge\frac{2n\log\!\left(2(f(x^0)-f^*)/\varepsilon\right)}{\varepsilon},k≥ε2nlog(2(f(x0)−f∗)/ε)​,

then f(xk)−f∗≤εf(x^k)-f^*\le\varepsilonf(xk)−f∗≤ε.

This gives the paper's explicit iteration count for reaching a prescribed optimality gap in D-optimal design.

Formalization Note Positive ε\varepsilonε makes the division and logarithm meaningful. The optimum is represented by an attained x∗x^*x∗ on the positive-definiteness domain; the run is over the positive simplex because the log barrier is infinite at the boundary in the paper. Iterates start at index zero.

Preamble
import Mathlib
import Definitions.Def_RelSmoothFOM_DOptimal_Setting
Formal statement
namespace RelSmoothFOM.DOptimal

/-- Theorem 4.1: iteration complexity for D-optimal design. -/
theorem theorem_4_1 {m n : ℕ} (H : Matrix (Fin m) (Fin n) ℝ)
    (hH : H.rank = m) (hmn : m + 1 ≤ n)
    (x : ℕ → Fin n → ℝ) (hx0 : x 0 = fun _ => 1 / (n : ℝ))
    (hrun : RelSmoothFOM.PrimalGrad.IsPrimalGradientRun (posSimplex n) (dOptObj H) logBarrier 1 x)
    (xstar : Fin n → ℝ) (hxs : xstar ∈ stdSimplex ℝ (Fin n))
    (hxspd : (H * Matrix.diagonal xstar * H.transpose).PosDef)
    (hopt : ∀ y ∈ stdSimplex ℝ (Fin n),
      (H * Matrix.diagonal y * H.transpose).PosDef →
        dOptObj H xstar ≤ dOptObj H y)
    (ε : ℝ) (hε : 0 < ε)
    (hεle : ε ≤ dOptObj H (x 0) - dOptObj H xstar)
    (k : ℕ)
    (hk : 2 * (n : ℝ) *
      Real.log (2 * (dOptObj H (x 0) - dOptObj H xstar) / ε) / ε ≤ (k : ℝ)) :
    dOptObj H (x k) - dOptObj H xstar ≤ ε := by sorry

end RelSmoothFOM.DOptimal
Source
Lu, Freund & Nesterov, Relatively smooth convex optimization by first-order methods, and applications, SIAM J. Optim. 28 (2018), p. 349, Theorem 4.1
Human review
  • Endorsed by Shuze Chen · Oct 9, 2026

    Confirmed by the moderator at approval.

  • Endorsed by mikedeng1 · Oct 9, 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