Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

centered_sampling_symmetrization_moment_bound_of_sample_ratio

Proved

by Shuze Chen · Jun 21, 2026 · Mathlib c5ea003 (Lean v4.30.0)

bernoulli-samplingcandes-rechtlean4matrix-completionrademachersection-6-1symmetrization

This is the sample-ratio-safe symmetrization estimate used in Section 6.1 of Candes-Recht.

For

p=mn1n2,SΩ(X)=p−1(PΩ−pI)X,p=\frac{m}{n_1n_2},\qquad S_\Omega(X)=p^{-1}(P_\Omega-pI)X,p=n1​n2​m​,SΩ​(X)=p−1(PΩ​−pI)X,

assuming 0<n10<n_10<n1​, 0<n20<n_20<n2​, and m≤n1n2m\le n_1n_2m≤n1​n2​, there is a universal constant Csym>0C_{\rm sym}>0Csym​>0 such that for every matrix XXX and every integer q≥1q\ge1q≥1,

EΩ ∥SΩ(X)∥q≤Csymq EΩEε∥p−1∑(i,j)∈ΩεijXijeiej⊤∥q.\mathbb E_\Omega\,\|S_\Omega(X)\|^q \le C_{\rm sym}^q\,\mathbb E_\Omega\mathbb E_\varepsilon \left\|p^{-1}\sum_{(i,j)\in\Omega}\varepsilon_{ij}X_{ij}e_ie_j^\top\right\|^q.EΩ​∥SΩ​(X)∥q≤Csymq​EΩ​Eε​​p−1(i,j)∈Ω∑​εij​Xij​ei​ej⊤​​q.

Source: Candes-Recht 2008, PDF p. 24, Section 6.1, equation (6.5), the Jensen independent-copy paragraph, the Rademacher symmetry of δ−δ′\delta-\delta'δ−δ′, and the displayed triangle-inequality estimate.

Preamble
import Definitions.Def_matrix_completion_rademacher
open MatrixCompletion
Formal statement
theorem centered_sampling_symmetrization_moment_bound_of_sample_ratio :
    ∃ Csym : ℝ, 0 < Csym ∧
      ∀ (n₁ n₂ m q : ℕ) (X : Matrix (Fin n₁) (Fin n₂) ℝ),
        0 < n₁ → 0 < n₂ → m ≤ n₁ * n₂ → 1 ≤ q →
        bernoulliExpectation ((m : ℝ) / ((n₁ : ℝ) * (n₂ : ℝ)))
            (fun Omega =>
              spectralNorm
                (centeredSamplingFluctuation Omega
                  ((m : ℝ) / ((n₁ : ℝ) * (n₂ : ℝ))) X) ^ q) ≤
          Csym ^ q *
            bernoulliExpectation ((m : ℝ) / ((n₁ : ℝ) * (n₂ : ℝ)))
              (fun Omega =>
                rademacherExpectation
                  (fun eps =>
                    spectralNorm
                      (rademacherSampledMatrix Omega eps
                        ((m : ℝ) / ((n₁ : ℝ) * (n₂ : ℝ))) X) ^ q)) := by
  sorry
Source
Candes, Emmanuel, and Benjamin Recht. "Exact matrix completion via convex optimization." Communications of the ACM 55.6 (2012): 111-119.

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