Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Stochastic analogue of (2.22) — α_k⟨G(x^md_k, ξ_k), x_{k−1} − x⟩ identity (p. 17)

Proved
NonconvexAG.Stoch.eq_2_22_stoch

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

accelerated-gradientconvex-optimizationp2o-batch-pfp2bp2o-gran-per-chapterp2o-plan-paperp2o-v1stochastic-approximation

Run the RSAG method (Algorithm 3) from x0x_0x0​ with step sizes α1=1\alpha_1=1α1​=1, αk∈(0,1)\alpha_k\in(0,1)αk​∈(0,1) (k≥2k\ge2k≥2), βk,λk>0\beta_k,\lambda_k>0βk​,λk​>0, any oracle and any noise sequence; let ggg be any map Rn→Rn\mathbb R^n\to\mathbb R^nRn→Rn (in the paper g=∇Ψg=\nabla\Psig=∇Ψ) and δk=G(xkmd,ξk)−g(xkmd)\delta_k=G(x^{md}_k,\xi_k)-g(x^{md}_k)δk​=G(xkmd​,ξk​)−g(xkmd​). Then for every sample point, every k≥1k\ge1k≥1 and every x∈Rnx\in\mathbb R^nx∈Rn,

αk⟨g(xkmd)+δk, xk−1−x⟩=αk2λk[∥xk−1−x∥2−∥xk−x∥2]+αkλk2∥g(xkmd)+δk∥2.\alpha_k\langle g(x^{md}_k)+\delta_k,\,x_{k-1}-x\rangle=\frac{\alpha_k}{2\lambda_k}\Big[\|x_{k-1}-x\|^2-\|x_k-x\|^2\Big]+\frac{\alpha_k\lambda_k}{2}\|g(x^{md}_k)+\delta_k\|^2 .αk​⟨g(xkmd​)+δk​,xk−1​−x⟩=2λk​αk​​[∥xk−1​−x∥2−∥xk​−x∥2]+2αk​λk​​∥g(xkmd​)+δk​∥2.

It is the three-point identity for the step (3.2), xk=xk−1−λkG(xkmd,ξk)x_k=x_{k-1}-\lambda_kG(x^{md}_k,\xi_k)xk​=xk−1​−λk​G(xkmd​,ξk​), which produces the telescoping distance terms of the convex analysis.

Formalization Note The identity is pathwise; g(xkmd)+δkg(x^{md}_k)+\delta_kg(xkmd​)+δk​ is the oracle output G(xkmd,ξk)G(x^{md}_k,\xi_k)G(xkmd​,ξk​).

Preamble
import Mathlib
import Definitions.Def_ConvexOptAlg_SmoothGD_Defs
import Definitions.Def_GhadimiLan_RSG_Model
import Definitions.Def_NonconvexAG_Stoch_RSAG
open MeasureTheory ProbabilityTheory
open scoped InnerProductSpace
Formal statement
namespace NonconvexAG.Stoch

open GhadimiLan.RSG (E)

/-- The stochastic analogue of (2.22) (proof of Theorem 3 b), p. 17, display "Similar to
(2.22)"), pathwise for every sample point `ω`, every `k ≥ 1` and every `x ∈ ℝⁿ`:
`αₖ⟨∇Ψ(x^md_k) + δₖ, x_{k−1} − x⟩ = (αₖ/(2λₖ))[‖x_{k−1} − x‖² − ‖xₖ − x‖²]
  + (αₖλₖ/2)‖∇Ψ(x^md_k) + δₖ‖²`. -/
theorem eq_2_22_stoch {n : ℕ} (g : E n → E n)
    {Ω Ξ : Type*} (G : E n → Ξ → E n) (ξ : ℕ → Ω → Ξ)
    (α β lam : ℕ → ℝ) (hstep : RSAGStepsizes α β lam) (x0 : E n) :
    ∀ k, 1 ≤ k → ∀ ω : Ω, ∀ x : E n,
      α k * ⟪g (xmdSeq G α β lam x0 ξ k ω) + delta G g α β lam x0 ξ k ω,
          xSeq G α β lam x0 ξ (k - 1) ω - x⟫_ℝ =
        α k / (2 * lam k) *
            (‖xSeq G α β lam x0 ξ (k - 1) ω - x‖ ^ 2 - ‖xSeq G α β lam x0 ξ k ω - x‖ ^ 2)
          + α k * lam k / 2 *
              ‖g (xmdSeq G α β lam x0 ξ k ω) + delta G g α β lam x0 ξ k ω‖ ^ 2 := by sorry

end NonconvexAG.Stoch
Source
Ghadimi & Lan, Accelerated Gradient Methods for Nonconvex Nonlinear and Stochastic Programming, arXiv:1310.3787v1, p. 17, §3.1, display "Similar to (2.22)"
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