Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

One-step descent of the RSAG method (proof of Theorem 3 a), p. 16)

Proved
NonconvexAG.Stoch.one_step

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

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

Let Ψ:Rn→R\Psi:\mathbb R^n\to\mathbb RΨ:Rn→R be differentiable with LΨL_\PsiLΨ​-Lipschitz gradient ∇Ψ\nabla\Psi∇Ψ. 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 GGG and any noise sequence, and write δk=G(xkmd,ξk)−∇Ψ(xkmd)\delta_k=G(x^{md}_k,\xi_k)-\nabla\Psi(x^{md}_k)δk​=G(xkmd​,ξk​)−∇Ψ(xkmd​). Then for every sample point and every k≥1k\ge1k≥1,

Ψ(xk)≤Ψ(xk−1)−λk(1−LΨλk)∥∇Ψ(xkmd)∥2+LΨ(1−αk)22∥xk−1ag−xk−1∥2+LΨλk22∥δk∥2−λk⟨∇Ψ(xk−1)−LΨλk∇Ψ(xkmd),δk⟩.\Psi(x_k)\le\Psi(x_{k-1})-\lambda_k(1-L_\Psi\lambda_k)\|\nabla\Psi(x^{md}_k)\|^2+\frac{L_\Psi(1-\alpha_k)^2}{2}\|x^{ag}_{k-1}-x_{k-1}\|^2+\frac{L_\Psi\lambda_k^2}{2}\|\delta_k\|^2-\lambda_k\big\langle\nabla\Psi(x_{k-1})-L_\Psi\lambda_k\nabla\Psi(x^{md}_k),\delta_k\big\rangle .Ψ(xk​)≤Ψ(xk−1​)−λk​(1−LΨ​λk​)∥∇Ψ(xkmd​)∥2+2LΨ​(1−αk​)2​∥xk−1ag​−xk−1​∥2+2LΨ​λk2​​∥δk​∥2−λk​⟨∇Ψ(xk−1​)−LΨ​λk​∇Ψ(xkmd​),δk​⟩.

This is the stochastic counterpart of (2.15): the descent of the long-step sequence xkx_kxk​ in one iteration, with the oracle error appearing through a quadratic term and a linear term that vanishes in conditional expectation.

Formalization Note The inequality is pathwise: it holds for every realization of the noise, so no probabilistic assumption is made. It is the outer ends of the paper's chain (the second display of the proof).

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)

/-- One-step descent of the RSAG method (proof of Theorem 3 a), p. 16, second display, outer
ends), pathwise for every sample point `ω` and every `k ≥ 1`, with
`δₖ = G(x^md_k, ξₖ) − ∇Ψ(x^md_k)`:
`Ψ(xₖ) ≤ Ψ(xₖ₋₁) − λₖ(1 − L_Ψλₖ)‖∇Ψ(x^md_k)‖² + (L_Ψ(1 − αₖ)²/2)‖x^ag_{k−1} − xₖ₋₁‖²
  + (L_Ψλₖ²/2)‖δₖ‖² − λₖ⟨∇Ψ(xₖ₋₁) − L_Ψλₖ∇Ψ(x^md_k), δₖ⟩`. -/
theorem one_step {n : ℕ} (Ψ : E n → ℝ) (g : E n → E n) (LΨ : ℝ)
    (hΨ : ConvexOptAlg.SmoothGD.IsBetaSmooth Ψ g LΨ)
    {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,
      Ψ (xSeq G α β lam x0 ξ k ω) ≤
        Ψ (xSeq G α β lam x0 ξ (k - 1) ω)
          - lam k * (1 - LΨ * lam k) * ‖g (xmdSeq G α β lam x0 ξ k ω)‖ ^ 2
          + LΨ * (1 - α k) ^ 2 / 2 *
              ‖xagSeq G α β lam x0 ξ (k - 1) ω - xSeq G α β lam x0 ξ (k - 1) ω‖ ^ 2
          + LΨ * lam k ^ 2 / 2 * ‖delta G g α β lam x0 ξ k ω‖ ^ 2
          - lam k * ⟪g (xSeq G α β lam x0 ξ (k - 1) ω)
                - (LΨ * lam k) • g (xmdSeq G α β lam x0 ξ k ω),
              delta G g α β lam x0 ξ k ω⟫_ℝ := by sorry

end NonconvexAG.Stoch
Source
Ghadimi & Lan, Accelerated Gradient Methods for Nonconvex Nonlinear and Stochastic Programming, arXiv:1310.3787v1, p. 16, §3.1, proof of Theorem 3 a), second display
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