Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Theorem 2.4(b) — two-phase RSG finds an (ε, Λ)-solution

Proved
GhadimiLan.TwoPhase.theorem_2_4_b

by mikedeng1 · Oct 8, 2026 · Mathlib 0df444a (Lean v4.33.1)

complexitynonconvex-optimizationp2o-batch-pfp2ap2o-gran-per-chapterp2o-plan-paperp2o-v1probabilitystochastic-approximation

Consider the two-phase RSG method of Theorem 2.4. Let ε>0\varepsilon>0ε>0 and 0<Λ<10<\Lambda<10<Λ<1, and set

S=⌈log⁡2(2/Λ)⌉,N=⌈max⁡{32L2Df2ε,[32L(D~+Df2/D~)σε]2}⌉,T=⌈24(S+1)σ2Λε⌉.S=\left\lceil\log_2(2/\Lambda)\right\rceil,\qquad N=\left\lceil\max\left\{\frac{32L^2D_f^2}{\varepsilon},\left[\frac{32L(\widetilde D+D_f^2/\widetilde D)\sigma}{\varepsilon}\right]^2\right\}\right\rceil,\qquad T=\left\lceil\frac{24(S+1)\sigma^2}{\Lambda\varepsilon}\right\rceil.S=⌈log2​(2/Λ)⌉,N=​max⎩⎨⎧​ε32L2Df2​​,[ε32L(D+Df2​/D)σ​]2⎭⎬⎫​​,T=⌈Λε24(S+1)σ2​⌉.

The selected candidate xˉ∗\bar x^*xˉ∗ is an (ε,Λ)(\varepsilon,\Lambda)(ε,Λ)-solution:

Pr⁡{∥∇f(xˉ∗)∥2≤ε}≥1−Λ.\Pr\{\|\nabla f(\bar x^*)\|^2\le\varepsilon\}\ge1-\Lambda.Pr{∥∇f(xˉ∗)∥2≤ε}≥1−Λ.

The algorithm uses at most S(N+T)S(N+T)S(N+T) stochastic first-order oracle calls: SSS runs of at most NNN calls, followed by TTT estimates for each candidate.

Formalization Note The call count follows from the modeled loops and is stated in prose rather than through a separate call-counting semantics. The logarithm in (2.24) is read in base two; the printed proof's 2−S≤Λ/22^{-S}\le\Lambda/22−S≤Λ/2 does not follow from a natural logarithm. The model has σ>0\sigma>0σ>0, since otherwise (2.13) and (2.26) yield a zero step or zero sample size in Lean.

Preamble
import Mathlib
import Definitions.Def_GhadimiLan_TwoPhase_Model
open MeasureTheory ProbabilityTheory
Formal statement
namespace GhadimiLan.TwoPhase

/-- Theorem 2.4(b), Eqs. (2.24)–(2.27), p. 12. The logarithm in (2.24)
is read in base two, as required by the paper's final 2⁻ˢ bound. -/
theorem theorem_2_4_b {n S N T : ℕ} {Ω Ξ : Type*}
    [MeasurableSpace Ω] [MeasurableSpace Ξ]
    (μ : Measure Ω) [IsProbabilityMeasure μ]
    (P : Problem n Ξ) (A : System (S := S) (N := N) (T := T) P μ)
    (ε Λ : ℝ) (hε : 0 < ε) (hΛ0 : 0 < Λ) (hΛ1 : Λ < 1)
    (hS : S = Nat.ceil (Real.logb 2 (2 / Λ)))
    (hN : N = Nat.ceil (max (32 * P.L ^ 2 * Df P ^ 2 / ε)
      ((32 * P.L * (P.Dt + Df P ^ 2 / P.Dt) * P.σ / ε) ^ 2)))
    (hT : T = Nat.ceil (24 * ((S : ℝ) + 1) * P.σ ^ 2 / (Λ * ε))) :
    ENNReal.ofReal (1 - Λ) ≤
      μ {ω | ‖P.g (chosen A ω)‖ ^ 2 ≤ ε} := by sorry

end GhadimiLan.TwoPhase
Source
Ghadimi & Lan, arXiv:1309.5549v1, Theorem 2.4(b), Eqs. (2.24)–(2.27), p. 12
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