Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Theorem 3 — robust regression over Ua\mathcal U_aUa​ equals min⁡x∥b−Ax∥a+∑ici∣xi∣\min_x \|b-Ax\|_a + \sum_i c_i|x_i|minx​∥b−Ax∥a​+∑i​ci​∣xi​∣ for an arbitrary norm

Proved
RobustRegLasso.Coupled.theorem_3_arbitrary_norm

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

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

Let ∥⋅∥a\|\cdot\|_a∥⋅∥a​ be an arbitrary norm on Rn\mathbb R^nRn with n≥1n \ge 1n≥1, let a1,…,am,b∈Rna_1,\dots,a_m, b \in \mathbb R^na1​,…,am​,b∈Rn be the columns of AAA and the response, and let c1,…,cm≥0c_1,\dots,c_m \ge 0c1​,…,cm​≥0 be budgets. Consider the feature-wise uncertainty set

Ua={(δ1,…,δm):∥δi∥a≤ci, i=1,…,m}.\mathcal U_a = \{(\delta_1,\dots,\delta_m) : \|\delta_i\|_a \le c_i,\ i=1,\dots,m\}.Ua​={(δ1​,…,δm​):∥δi​∥a​≤ci​, i=1,…,m}.

Then the robust regression problem min⁡xmax⁡ΔA∈Ua∥b−(A+ΔA)x∥a\min_x \max_{\Delta A \in \mathcal U_a} \|b - (A+\Delta A)x\|_aminx​maxΔA∈Ua​​∥b−(A+ΔA)x∥a​ is equivalent to the regularized regression problem

min⁡x∈Rm{∥b−Ax∥a+∑i=1mci∣xi∣}\min_{x \in \mathbb R^m} \Big\{ \|b - Ax\|_a + \sum_{i=1}^m c_i |x_i| \Big\}x∈Rmmin​{∥b−Ax∥a​+i=1∑m​ci​∣xi​∣}

in the following sense:

  1. for every x∈Rmx \in \mathbb R^mx∈Rm, the maximum of ∥b−(A+ΔA)x∥a\|b-(A+\Delta A)x\|_a∥b−(A+ΔA)x∥a​ over ΔA∈Ua\Delta A \in \mathcal U_aΔA∈Ua​ is attained and equals ∥b−Ax∥a+∑ici∣xi∣\|b-Ax\|_a + \sum_i c_i|x_i|∥b−Ax∥a​+∑i​ci​∣xi​∣;
  2. a vector xxx minimizes the robust objective if and only if it minimizes the regularized objective.

This is Theorem 1 with the Euclidean norm replaced by an arbitrary norm; it is the step of the proof of (13) that evaluates the inner maximum for fixed budgets.

Formalization Note. (Rn,∥⋅∥a)(\mathbb R^n, \|\cdot\|_a)(Rn,∥⋅∥a​) is an arbitrary nontrivial real normed space EEE (the nontriviality is the paper's implicit n≥1n \ge 1n≥1; with n=0n = 0n=0 the identity fails). The budgets ci≥0c_i \ge 0ci​≥0 come from the setting of (2). "Is equivalent to" is read as: equal objectives at every xxx (with the maximum attained) and equal sets of minimizers; existence of a minimizer is not claimed. The robust objective in the minimizer clause is the extended-real supremum.

Preamble
import Mathlib
import Definitions.Def_RobustRegLasso_Coupled_Basic
Formal statement
namespace RobustRegLasso.Coupled

/-- Theorem 3 of arXiv:0811.1790v1, p. 6. For an arbitrary norm `‖·‖ₐ` on `E` (with `E ≠ 0`, i.e.
`n ≥ 1`) and budgets `cᵢ ≥ 0`, the robust regression problem over
`Uₐ = {(δ₁, …, δₘ) | ‖δᵢ‖ₐ ≤ cᵢ}` is equivalent to the regularized problem
`min_x ‖b − Ax‖ₐ + ∑ᵢ cᵢ|xᵢ|`: for every `x` the worst-case residual is attained and equals
`‖b − Ax‖ₐ + ∑ᵢ cᵢ|xᵢ|`, and the two problems have the same minimizers. -/
theorem theorem_3_arbitrary_norm {E : Type*} [NormedAddCommGroup E] [NormedSpace ℝ E]
    [Nontrivial E] {m : ℕ} (a : Fin m → E) (b : E) (c : Fin m → ℝ) (hc : ∀ i, 0 ≤ c i) :
    (∀ x : Fin m → ℝ,
      IsGreatest (residualValues a b (uncertaintySetA c) x)
        (‖b - matVec a x‖ + ∑ i, c i * |x i|)) ∧
    {x : Fin m → ℝ | ∀ x' : Fin m → ℝ,
        robustObjective a b (uncertaintySetA c) x ≤ robustObjective a b (uncertaintySetA c) x'} =
      {x : Fin m → ℝ | ∀ x' : Fin m → ℝ,
        ‖b - matVec a x‖ + ∑ i, c i * |x i| ≤ ‖b - matVec a x'‖ + ∑ i, c i * |x' i|} := by sorry

end RobustRegLasso.Coupled
Source
Xu, Caramanis, Mannor, Robust Regression and Lasso, arXiv:0811.1790v1, p. 6, Theorem 3
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