Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Proof of Theorem 5′, second display — A+U⊆A~+U~A+\mathcal U\subseteq\tilde A+\tilde{\mathcal U}A+U⊆A~+U~ as sets of perturbed matrices, hence RA~,U~≥RA,UR_{\tilde A,\tilde{\mathcal U}}\ge R_{A,\mathcal U}RA~,U~​≥RA,U​

Proved
RobustRegLasso.Sparsity.theorem_5_prime_inclusion

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

p2o-batch-pfp2bp2o-gran-per-chapterp2o-plan-paperp2o-v1regressionrobust-optimizationsparsity

Let a1,…,am,a~1,…,a~m,b∈Rna_1,\dots,a_m, \tilde a_1,\dots,\tilde a_m, b \in \mathbb R^na1​,…,am​,a~1​,…,a~m​,b∈Rn, radii cic_ici​, numbers ljl_jlj​, and an index set I⊆{1,…,m}I \subseteq \{1,\dots,m\}I⊆{1,…,m}, with ∥aj−a~j∥2≤lj\|a_j - \tilde a_j\|_2 \le l_j∥aj​−a~j​∥2​≤lj​ for j∉Ij \notin Ij∈/I and ai=a~ia_i = \tilde a_iai​=a~i​ for i∈Ii \in Ii∈I. Then

{A+ΔA∣ΔA∈U}⊆{A~+ΔA∣ΔA∈U~},\{A + \Delta A \mid \Delta A \in \mathcal U\} \subseteq \{\tilde A + \Delta A \mid \Delta A \in \tilde{\mathcal U}\},{A+ΔA∣ΔA∈U}⊆{A~+ΔA∣ΔA∈U~},

and consequently, for every x′∈Rmx' \in \mathbb R^mx′∈Rm,

max⁡ΔA∈U~∥b−(A~+ΔA)x′∥2 ≥ max⁡ΔA∈U∥b−(A+ΔA)x′∥2.\max_{\Delta A\in\tilde{\mathcal U}} \|b-(\tilde A+\Delta A)x'\|_2 \ \ge\ \max_{\Delta A\in\mathcal U} \|b-(A+\Delta A)x'\|_2.ΔA∈U~max​∥b−(A~+ΔA)x′∥2​ ≥ ΔA∈Umax​∥b−(A+ΔA)x′∥2​.

This is the second step of the proof of Theorem 5′: enlarging the bounds on the features outside III by ljl_jlj​ absorbs the change from AAA to A~\tilde AA~, so the worst case for (A~,U~)(\tilde A, \tilde{\mathcal U})(A~,U~) dominates the worst case for (A,U)(A, \mathcal U)(A,U) at every point.

Formalization Note The printed display reads max⁡ΔA∈U~∥b−(A+ΔA)x′∥2≥max⁡ΔA∈U∥b−(A~+ΔA)x′∥2\max_{\Delta A\in\tilde{\mathcal U}}\|b-(A+\Delta A)x'\|_2 \ge \max_{\Delta A\in\mathcal U}\|b-(\tilde A+\Delta A)x'\|_2maxΔA∈U~​∥b−(A+ΔA)x′∥2​≥maxΔA∈U​∥b−(A~+ΔA)x′∥2​, with AAA and A~\tilde AA~ exchanged relative to the inclusion that justifies it and to the final display of the proof that uses it. The version stated here is the one the inclusion gives and the proof uses (the printed one is also true, by the symmetric inclusion). Matrices are column families, so A+ΔAA + \Delta AA+ΔA is the family (ai+δi)i(a_i + \delta_i)_i(ai​+δi​)i​. Maxima are suprema in EReal. No sign condition on ccc or lll is needed.

Preamble
import Mathlib
import Definitions.Def_RobustRegLasso_Sparsity_Basic
Formal statement
namespace RobustRegLasso.Sparsity

theorem theorem_5_prime_inclusion {n m : ℕ} (a aTilde : Fin m → EuclideanSpace ℝ (Fin n))
    (b : EuclideanSpace ℝ (Fin n)) (c l : Fin m → ℝ) (I : Finset (Fin m))
    (hl : ∀ j, j ∉ I → ‖a j - aTilde j‖ ≤ l j) (hI : ∀ i, i ∈ I → a i = aTilde i) :
    {M | ∃ δ ∈ (RobustRegLasso.FeatureWise.uncertaintySet c : Set (Fin m → EuclideanSpace ℝ (Fin n))), M = a + δ} ⊆
      {M | ∃ δ ∈ (enlargedSet c l I : Set (Fin m → EuclideanSpace ℝ (Fin n))), M = aTilde + δ} ∧
    ∀ x' : Fin m → ℝ, robustObjective a b (RobustRegLasso.FeatureWise.uncertaintySet c) x' ≤
      robustObjective aTilde b (enlargedSet c l I) x' := by sorry

end RobustRegLasso.Sparsity
Source
Xu, Caramanis, Mannor, Robust Regression and Lasso, arXiv:0811.1790v1, p. 9, proof of Theorem 5′, second display and inclusion
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