Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Proof of Theorem 1 — for every x, max over U of ‖b − (A + ΔA)x‖₂ equals ‖b − Ax‖₂ + Σ cᵢ|xᵢ|, attained

Proved
RobustRegLasso.FeatureWise.per_x_identity

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

lassop2o-batch-pfp2bp2o-gran-per-chapterp2o-plan-paperp2o-v1regressionrobust-optimization

Let n≥1n\ge1n≥1, let A∈Rn×mA\in\mathbb R^{n\times m}A∈Rn×m have columns a1,…,ama_1,\dots,a_ma1​,…,am​, let b∈Rnb\in\mathbb R^nb∈Rn, let c1,…,cm≥0c_1,\dots,c_m\ge 0c1​,…,cm​≥0, and let U={(δ1,…,δm):∥δi∥2≤ci}\mathcal U=\{(\delta_1,\dots,\delta_m):\|\delta_i\|_2\le c_i\}U={(δ1​,…,δm​):∥δi​∥2​≤ci​} be the uncertainty set (2). For every x∈Rmx\in\mathbb R^mx∈Rm the worst-case residual is a maximum, and

max⁡ΔA∈U∥b−(A+ΔA)x∥2=∥b−Ax∥2+∑i=1mci∣xi∣.\max_{\Delta A\in\mathcal U}\|b-(A+\Delta A)x\|_2 = \|b-Ax\|_2 + \sum_{i=1}^m c_i|x_i| .ΔA∈Umax​∥b−(A+ΔA)x∥2​=∥b−Ax∥2​+i=1∑m​ci​∣xi​∣.

That is, the number ∥b−Ax∥2+∑ici∣xi∣\|b-Ax\|_2+\sum_i c_i|x_i|∥b−Ax∥2​+∑i​ci​∣xi​∣ belongs to the set {∥b−(A+ΔA)x∥2:ΔA∈U}\{\|b-(A+\Delta A)x\|_2 : \Delta A\in\mathcal U\}{∥b−(A+ΔA)x∥2​:ΔA∈U} and bounds it from above; equivalently, the robust objective R(x)=sup⁡ΔA∈U∥b−(A+ΔA)x∥2R(x)=\sup_{\Delta A\in\mathcal U}\|b-(A+\Delta A)x\|_2R(x)=supΔA∈U​∥b−(A+ΔA)x∥2​ equals the ℓ¹-regularized objective L(x)L(x)L(x).

This per-point identity is the heart of Theorem 1: the robust regression objective and the ℓ¹-regularized objective are the same function of xxx.

Formalization Note "max" is stated as IsGreatest of the set of residual norms (the maximum exists and has this value), together with the equality of the EReal supremum R(x)R(x)R(x) and L(x)L(x)L(x). The paper leaves n≥1n\ge1n≥1 implicit; for n=0n=0n=0 the identity would read 0=∑ici∣xi∣0=\sum_i c_i|x_i|0=∑i​ci​∣xi​∣ and is false, so 0 < n is a hypothesis.

Preamble
import Mathlib
import Definitions.Def_RobustRegLasso_FeatureWise_Basic
Formal statement
namespace RobustRegLasso.FeatureWise

theorem per_x_identity {n m : ℕ} (hn : 0 < n) (a : Fin m → EuclideanSpace ℝ (Fin n))
    (b : EuclideanSpace ℝ (Fin n)) (c : Fin m → ℝ) (hc : ∀ i, 0 ≤ c i) (x : Fin m → ℝ) :
    IsGreatest (residualValues a b c x) (‖b - matVec a x‖ + ∑ i, c i * |x i|) ∧
      robustObjective a b c x = ((‖b - matVec a x‖ + ∑ i, c i * |x i| : ℝ) : EReal) := by sorry

end RobustRegLasso.FeatureWise
Source
Xu, Caramanis, Mannor, Robust Regression and Lasso, arXiv:0811.1790v1, p. 4, proof of Theorem 1, first sentence ("Fix x∗. We prove that …") and closing sentence ("Combining Inequalities (4) and (5) …")
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