Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Proposition 2 — supermartingale convergence theorem: E{Yk+1∣Fk}≤Yk−Zk+WkE\{Y_{k+1}\mid\mathcal F_k\}\le Y_k-Z_k+W_kE{Yk+1​∣Fk​}≤Yk​−Zk​+Wk​, ∑Wk<∞\sum W_k<\infty∑Wk​<∞ ⇒ ∑Zk<∞\sum Z_k<\infty∑Zk​<∞, YkY_kYk​ converges

Proved
IncProx.Randomized.proposition2

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

martingalesp2o-batch-pfp2bp2o-gran-per-chapterp2o-plan-paperp2o-v1probabilitystochastic-optimization

Let (Ω,F,μ)(\Omega,\mathcal F,\mu)(Ω,F,μ) be a probability space with a filtration F0⊆F1⊆⋯⊆F\mathcal F_0\subseteq\mathcal F_1\subseteq\cdots\subseteq\mathcal FF0​⊆F1​⊆⋯⊆F, and let Yk,Zk,WkY_k,Z_k,W_kYk​,Zk​,Wk​, k=0,1,…k=0,1,\dotsk=0,1,…, be real random variables such that:

  1. YkY_kYk​, ZkZ_kZk​, WkW_kWk​ are nonnegative and Fk\mathcal F_kFk​-measurable;
  2. for each kkk, almost surely,
E{Yk+1∣Fk}≤Yk−Zk+Wk;E\{Y_{k+1}\mid\mathcal F_k\}\le Y_k-Z_k+W_k;E{Yk+1​∣Fk​}≤Yk​−Zk​+Wk​;
  1. with probability 1, ∑k=0∞Wk<∞\sum_{k=0}^\infty W_k<\infty∑k=0∞​Wk​<∞.

Then, with probability 1, ∑k=0∞Zk<∞\sum_{k=0}^\infty Z_k<\infty∑k=0∞​Zk​<∞, and the sequence YkY_kYk​ converges to a nonnegative (finite) random variable YYY.

This is the special case of the Robbins–Siegmund theorem that the paper cites from the literature and uses in the analysis of the randomized methods: applied with Yk=∥xk−x∗∥2Y_k=\|x_k-x^*\|^2Yk​=∥xk​−x∗∥2 it turns the conditional descent inequality (58) into the almost sure statement (59).

Formalization Note The paper's "sets of random variables Fk⊂Fk+1\mathcal F_k\subset\mathcal F_{k+1}Fk​⊂Fk+1​" are read as the σ\sigmaσ-algebras they generate, i.e. a filtration, and "functions of the random variables in Fk\mathcal F_kFk​" as adaptedness. Integrability of each YkY_kYk​ is an added hypothesis: Lean's conditional expectation of a non-integrable function is 000, so without it condition 2 would not express the paper's inequality. In the application YkY_kYk​ is integrable. Nonnegativity is required pointwise.

Preamble
import Mathlib
Formal statement
namespace IncProx.Randomized

open Filter Topology MeasureTheory

/-- Proposition 2 (Supermartingale Convergence Theorem, p. 8). `Y`, `Z`, `W` are nonnegative and
adapted to the filtration `𝓕` (F_k ⊂ F_{k+1}); `E{Y_{k+1} | F_k} ≤ Y_k − Z_k + W_k`;
`Σ W_k < ∞` with probability 1. Then with probability 1 `Σ Z_k < ∞` and `Y_k` converges to a
nonnegative random variable. Integrability of each `Y_k` is an added hypothesis (Lean's conditional
expectation of a non-integrable function is `0`). -/
theorem proposition2 {Ω : Type*} {m0 : MeasurableSpace Ω} (μ : Measure Ω) [IsProbabilityMeasure μ]
    (𝓕 : Filtration ℕ m0) (Y Z W : ℕ → Ω → ℝ)
    (hYad : Adapted 𝓕 Y) (hZad : Adapted 𝓕 Z) (hWad : Adapted 𝓕 W)
    (hY0 : ∀ k s, 0 ≤ Y k s) (hZ0 : ∀ k s, 0 ≤ Z k s) (hW0 : ∀ k s, 0 ≤ W k s)
    (hYint : ∀ k, Integrable (Y k) μ)
    (h2 : ∀ k, μ[Y (k + 1) | 𝓕 k] ≤ᵐ[μ] fun s => Y k s - Z k s + W k s)
    (h3 : ∀ᵐ s ∂μ, Summable fun k => W k s) :
    (∀ᵐ s ∂μ, Summable fun k => Z k s) ∧
      ∃ Yinf : Ω → ℝ, Measurable Yinf ∧
        ∀ᵐ s ∂μ, 0 ≤ Yinf s ∧ Tendsto (fun k => Y k s) atTop (𝓝 (Yinf s)) := by sorry

end IncProx.Randomized
Source
Bertsekas, Incremental Proximal Methods for Large Scale Convex Optimization, LIDS-P-2847 (rev. March 2011), p. 8, Proposition 2
Human review
  • Endorsed by Shuze Chen · Oct 8, 2026

    Confirmed by the moderator at approval.

  • Endorsed by mikedeng1 · Oct 8, 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