Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Stochastic analogue of (2.17) — ‖x^ag_{k−1} − x_{k−1}‖² ≤ Γ_{k−1} Σ_τ ((λ_τ − β_τ)²/(Γ_τα_τ))‖∇Ψ(x^md_τ) + δ_τ‖² (p. 16)

Proved
NonconvexAG.Stoch.eq_2_17_stoch

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

accelerated-gradientnonconvex-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 GGG 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 δτ=G(xτmd,ξτ)−g(xτmd)\delta_\tau=G(x^{md}_\tau,\xi_\tau)-g(x^{md}_\tau)δτ​=G(xτmd​,ξτ​)−g(xτmd​). Then for every sample point and every k≥1k\ge1k≥1,

∥xk−1ag−xk−1∥2≤Γk−1∑τ=1k−1(λτ−βτ)2Γτατ[∥g(xτmd)∥2+∥δτ∥2+2⟨g(xτmd),δτ⟩].\|x^{ag}_{k-1}-x_{k-1}\|^2\le\Gamma_{k-1}\sum_{\tau=1}^{k-1}\frac{(\lambda_\tau-\beta_\tau)^2}{\Gamma_\tau\alpha_\tau}\Big[\|g(x^{md}_\tau)\|^2+\|\delta_\tau\|^2+2\langle g(x^{md}_\tau),\delta_\tau\rangle\Big].∥xk−1ag​−xk−1​∥2≤Γk−1​τ=1∑k−1​Γτ​ατ​(λτ​−βτ​)2​[∥g(xτmd​)∥2+∥δτ​∥2+2⟨g(xτmd​),δτ​⟩].

It bounds the gap between the two sequences of the method by the past stochastic gradients G(xτmd,ξτ)=g(xτmd)+δτG(x^{md}_\tau,\xi_\tau)=g(x^{md}_\tau)+\delta_\tauG(xτmd​,ξτ​)=g(xτmd​)+δτ​; combined with the one-step inequality it yields the summed bound of the proof of Theorem 3 a).

Formalization Note The inequality is pathwise. At k=1k=1k=1 both sides are 000. The paper prints ∥∇Ψ(xτmd)+δk∥2\|\nabla\Psi(x^{md}_\tau)+\delta_k\|^2∥∇Ψ(xτmd​)+δk​∥2 in the first line of its display; the index of δ\deltaδ there is τ\tauτ, as the second line of the same display shows, and the Lean states the second line.

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 (2.17) (proof of Theorem 3 a), p. 16, display "Noting that
similar to (2.17)", outer ends, with the printed `δₖ` inside the first sum read as `δ_τ`),
pathwise for every sample point `ω` and every `k ≥ 1`:
`‖x^ag_{k−1} − x_{k−1}‖² ≤ Γ_{k−1} Σ_{τ=1}^{k−1} ((λ_τ − β_τ)²/(Γ_τα_τ))
  [‖∇Ψ(x^md_τ)‖² + ‖δ_τ‖² + 2⟨∇Ψ(x^md_τ), δ_τ⟩]`. -/
theorem eq_2_17_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,
      ‖xagSeq G α β lam x0 ξ (k - 1) ω - xSeq G α β lam x0 ξ (k - 1) ω‖ ^ 2 ≤
        NonconvexAG.Smooth.Gamma α (k - 1) * ∑ τ ∈ Finset.Icc 1 (k - 1),
          (lam τ - β τ) ^ 2 / (NonconvexAG.Smooth.Gamma α τ * α τ) *
            (‖g (xmdSeq G α β lam x0 ξ τ ω)‖ ^ 2 + ‖delta G g α β lam x0 ξ τ ω‖ ^ 2
              + 2 * ⟪g (xmdSeq G α β lam x0 ξ τ ω), delta G g α β lam x0 ξ τ 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, display "Noting that similar to (2.17)"
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