Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

(4.4) — f(x)−f(Vi(x))≥Li2∥u(i)(x)−x(i)∥(i)2f(x)-f(V_i(x))\ge\frac{L_i}2\|u^{(i)}(x)-x^{(i)}\|_{(i)}^2f(x)−f(Vi​(x))≥2Li​​∥u(i)(x)−x(i)∥(i)2​

Proved
NesterovRCD.Constrained.eq_4_4

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

constrained-optimizationconvex-optimizationcoordinate-descentp2o-batch-pfp2bp2o-gran-per-chapterp2o-plan-paperp2o-v1

In the setting of §4 — Q=Q1×⋯×QnQ=Q_1\times\cdots\times Q_nQ=Q1​×⋯×Qn​ with each Qi⊆RniQ_i\subseteq\mathbb R^{n_i}Qi​⊆Rni​ nonempty, closed and convex, Euclidean block norms (3.4), and fff convex with coordinate-wise Lipschitz gradient (2.2), constants Li>0L_i>0Li​>0 — let u(i)(x)u^{(i)}(x)u(i)(x) and Vi(x)=x+Ui(u(i)(x)−x(i))V_i(x)=x+U_i(u^{(i)}(x)-x^{(i)})Vi​(x)=x+Ui​(u(i)(x)−x(i)) be the constrained coordinate update (4.2). Then for every feasible point x∈Qx\in Qx∈Q and every block iii,

f(x)−f(Vi(x))≥Li2 ∥u(i)(x)−x(i)∥(i)2.f(x)-f(V_i(x))\ge\frac{L_i}2\,\big\|u^{(i)}(x)-x^{(i)}\big\|_{(i)}^2 .f(x)−f(Vi​(x))≥2Li​​​u(i)(x)−x(i)​(i)2​.

Each step of the constrained method therefore does not increase the objective, and decreases it in proportion to the squared length of the step. It makes the expected values φk\varphi_kφk​ of UCDM nonincreasing.

Formalization Note The paper writes xix^ixi for x(i)x^{(i)}x(i) in the derivation (a typo). The hypothesis x∈Qx\in Qx∈Q is implicit in the paper, whose derivation substitutes u(i)=x(i)u^{(i)}=x^{(i)}u(i)=x(i) into (4.3), which requires x(i)∈Qix^{(i)}\in Q_ix(i)∈Qi​; it is stated. The standing assumptions of §4 are stated as for (4.3), together with Qi≠∅Q_i\ne\emptysetQi​=∅ and n≥1n\ge1n≥1. Indices are Fin n, 0-based.

Preamble
import Mathlib
import Definitions.Def_NesterovRCD_HighProb_Basic
import Definitions.Def_NesterovRCD_Constrained_UCDM
Formal statement
namespace NesterovRCD.Constrained

variable {n : ℕ} {E : Fin n → Type*} [∀ i, NormedAddCommGroup (E i)] [∀ i, InnerProductSpace ℝ (E i)]
  [∀ i, FiniteDimensional ℝ (E i)]

theorem eq_4_4 (hn : 0 < n) (f : NesterovRCD.Sublinear.Blocks E → ℝ) (L : Fin n → ℝ)
    (hf : ConvexOn ℝ Set.univ f) (hL : NesterovRCD.Sublinear.CoordLipschitz f L)
    (Q : ∀ i, Set (E i)) (hQc : ∀ i, IsClosed (Q i)) (hQv : ∀ i, Convex ℝ (Q i))
    (hQne : ∀ i, (Q i).Nonempty) (x : NesterovRCD.Sublinear.Blocks E) (hx : x ∈ Qset Q) (i : Fin n) :
    L i / 2 * ‖blockUpdate f L Q x i - x i‖ ^ 2 ≤ f x - f (constrStep f L Q i x) := by sorry

end NesterovRCD.Constrained
Source
Nesterov, Efficiency of coordinate descent methods on huge-scale optimization problems, CORE Discussion Paper 2010/2, p. 13, §4, (4.4)
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