Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Theorem 3.3 — every accumulation point of the greedy sparse-simplex method is a coordinate-wise minimum of (P)

Proved
SparseNLO.Greedy.theorem_3_3

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

coordinate-descentnonconvex-optimizationp2o-batch-pfp2bp2o-gran-per-chapterp2o-plan-paperp2o-v1sparse-optimization

Let f:Rn→Rf:\mathbb R^n\to\mathbb Rf:Rn→R be continuously differentiable and bounded below (Assumption 1), and let 0<s<n0<s<n0<s<n be an integer. Consider the sparsity constrained problem

(P)min⁡ f(x)s.t.∥x∥0≤s.(\mathrm P)\qquad \min\ f(x)\quad\text{s.t.}\quad \|x\|_0\le s .(P)min f(x)s.t.∥x∥0​≤s.

Let (xk)k≥0(x^k)_{k\ge0}(xk)k≥0​ be a sequence generated by the greedy sparse-simplex method. Then every accumulation point x∗x^*x∗ of (xk)(x^k)(xk) is a coordinate-wise minimum of (P) (Definition 2.4): x∗∈Csx^*\in C_sx∗∈Cs​, and

  1. if ∥x∗∥0<s\|x^*\|_0<s∥x∗∥0​<s, then f(x∗)≤f(x∗+tei)f(x^*)\le f(x^*+te_i)f(x∗)≤f(x∗+tei​) for every iii and every t∈Rt\in\mathbb Rt∈R;
  2. if ∥x∗∥0=s\|x^*\|_0=s∥x∗∥0​=s, then f(x∗)≤f(x∗−xi∗ei+tej)f(x^*)\le f(x^*-x^*_ie_i+te_j)f(x∗)≤f(x∗−xi∗​ei​+tej​) for every i∈I1(x∗)i\in I_1(x^*)i∈I1​(x∗), every jjj and every t∈Rt\in\mathbb Rt∈R.

The theorem needs no Lipschitz assumption on ∇f\nabla f∇f. Combined with Theorem 2.4 (every CW-minimum is an L2(f)L_2(f)L2​(f)-stationary point), it shows that under Assumption 2 the limit points of the method are L2(f)L_2(f)L2​(f)-stationary points (Corollary 3.2), without knowledge of any Lipschitz constant.

Formalization Note A run of the method is any sequence satisfying the step rule, with every choice of minimizers allowed, and a STOP modelled as xk+1=xkx^{k+1}=x^kxk+1=xk; the theorem holds for every run. "Accumulation point" is MapClusterPt xstar atTop x. Indices are 0,…,n−10,\dots,n-10,…,n−1 and teite_itei​ is EuclideanSpace.single i t.

Preamble
import Definitions.Def_SparseNLO_Greedy_Method

open Filter Topology
Formal statement
namespace SparseNLO.Greedy

/-- Theorem 3.3 (p. 19): let `{xᵏ}` be a sequence generated by the greedy sparse-simplex method
for (P), where `f` is continuously differentiable and bounded below (Assumption 1) and
`0 < s < n`. Then every accumulation point of `{xᵏ}` is a CW-minimum of (P). -/
theorem theorem_3_3
    {n s : ℕ} (f : EuclideanSpace ℝ (Fin n) → ℝ) (hf : ContDiff ℝ 1 f)
    (hbdd : ∃ γ : ℝ, ∀ x, γ ≤ f x) (hs : 0 < s) (hsn : s < n)
    (x : ℕ → EuclideanSpace ℝ (Fin n)) (hrun : IsGreedyRun f s x)
    (xstar : EuclideanSpace ℝ (Fin n)) (hacc : MapClusterPt xstar atTop x) :
    SparseNLO.CWOpt.IsCWMin f s xstar := by sorry

end SparseNLO.Greedy
Source
Beck, Eldar, Sparsity Constrained Nonlinear Optimization: Optimality Conditions and Algorithms, SIAM J. Optim. (2013), doi:10.1137/120869778 (source: arXiv:1203.4580v1), p. 19, Theorem 3.3 (proof §4.2.1, pp. 29–30)
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