Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Proof of Theorem 7 — one RACDM iteration decreases fff by at least 3(∇if(x))2/(8Li)3(\nabla_if(x))^2/(8L_i)3(∇i​f(x))2/(8Li​)

Proved
NesterovRCD.Adaptive.step_decrease

by mikedeng1 · Oct 7, 2026 · Mathlib 0df444a (Lean v4.33.1)

backtrackingconvex-optimizationcoordinate-descentp2o-batch-pfp2bp2o-gran-per-chapterp2o-plan-paperp2o-v1

Let f:Rn→Rf:\mathbb R^n\to\mathbb Rf:Rn→R be convex and differentiable with coordinate-wise Lipschitz partial derivatives (2.2) with constants L1,…,LnL_1,\dots,L_nL1​,…,Ln​. Let x∈Rnx\in\mathbb R^nx∈Rn, let L^\hat LL^ be a vector of estimates, and let iii be a coordinate with 0<L^i≤Li0<\hat L_i\le L_i0<L^i​≤Li​. If x+x^+x+ is the point produced by one iteration of RACDM (6.1) on coordinate iii from the state (x,L^)(x,\hat L)(x,L^) (doubling loop, then the step with the accepted estimate), then

f(x)−f(x+) ≥ 38Li (∇if(x))2.f(x)-f(x^+)\ \ge\ \frac{3}{8L_i}\,\big(\nabla_i f(x)\big)^2 .f(x)−f(x+) ≥ 8Li​3​(∇i​f(x))2.

This is the one-step decrease in the proof of Theorem 7 (p. 19). It replaces the bound f(x)−f(Ti(x))≥(∇if(x))2/(2Li)f(x)-f(T_i(x))\ge(\nabla_if(x))^2/(2L_i)f(x)−f(Ti​(x))≥(∇i​f(x))2/(2Li​) of (2.4) for the step with the known constant LiL_iLi​; the factor 3/83/83/8 instead of 1/21/21/2 is the price of not knowing LiL_iLi​.

Formalization Note Rn\mathbb R^nRn is EuclideanSpace ℝ (Fin n) (scalar coordinates: the paper sets N=nN=nN=n in §6.1), coordinates are indexed 0,…,n−10,\dots,n-10,…,n−1 for the paper's 1,…,n1,\dots,n1,…,n, and the gradient is an explicit map ggg with g(x)=∇f(x)g(x)=\nabla f(x)g(x)=∇f(x), as in the published definition ConvexOptAlg_CoordDescent_Defs that this mission reuses (its IsCoordSmooth f g L is (2.2) with one-dimensional blocks and ∣⋅∣|\cdot|∣⋅∣ as block norm; it includes differentiability). The paper derives the bound from inequality (2.1.17) of Nesterov's Introductory Lectures, which needs the convexity of fff along the coordinate line; convexity of fff is the paper's standing assumption (2.1) and is a hypothesis here. In the paper the entry condition L^ik≤Lik\hat L_{i_k}\le L_{i_k}L^ik​​≤Lik​​ comes from item 1; here it is a hypothesis on an arbitrary state, together with L^i>0\hat L_i>0L^i​>0 (implicit in the paper).

Preamble
import Mathlib
import Definitions.Def_ConvexOptAlg_CoordDescent_Defs
import Definitions.Def_NesterovRCD_Adaptive_RACDM
Formal statement
namespace NesterovRCD.Adaptive

open ConvexOptAlg.CoordDescent

/-- Proof of Theorem 7, p. 19: for convex `f`, one iteration of RACDM (6.1) on coordinate `i`
from `(x, L̂)` with `0 < L̂_i ≤ L_i` decreases `f` by at least `3 (∇_i f(x))² / (8 L_i)`. -/
theorem step_decrease {n : ℕ} (f : Vec n → ℝ) (g : Vec n → Vec n)
    (hconv : ConvexOn ℝ Set.univ f) (L : Fin n → ℝ) (hL : IsCoordSmooth f g L)
    (x : Vec n) (Lh : Fin n → ℝ) (i : Fin n) (hpos : 0 < Lh i) (hle : Lh i ≤ L i) :
    3 / (8 * L i) * g x i ^ 2 ≤ f x - f (racdmStep g (x, Lh) i).1 := by sorry

end NesterovRCD.Adaptive
Source
Nesterov, Efficiency of coordinate descent methods on huge-scale optimization problems, CORE Discussion Paper 2010/2, p. 19, proof of Theorem 7 (first display)
Human review
  • Endorsed by Shuze Chen · Oct 7, 2026

    Confirmed by the moderator at approval.

  • Endorsed by mikedeng1 · Oct 7, 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