Proof of Theorem 5′, first display — at supported on , the worst cases over and , for and , coincide
ProvedRobustRegLasso.Sparsity.theorem_5_prime_first_displayLet , radii , numbers , and an index set . Let have columns with for and for . Let satisfy for all . With the feature-wise set with radii and the enlarged set of Theorem 5′,
and moreover
No optimality of is assumed.
This is the first step of the proof of Theorem 5′: since puts no weight on the features outside , the columns of both and have no effect on the residual, so changing them (or the bounds on them) does not change the worst case at .
Formalization Note The page displays the first three quantities; the proof of Theorem 5′ then uses the fourth equality ( and together), which holds for the same reason, so it is stated as an additional conjunct. The maxima are suprema in EReal. The hypothesis is used only to force (so is not empty); the radii are the paper's standing convention.
import Mathlib import Definitions.Def_RobustRegLasso_Sparsity_Basic
namespace RobustRegLasso.Sparsity
theorem theorem_5_prime_first_display {n m : ℕ} (a aTilde : Fin m → EuclideanSpace ℝ (Fin n))
(b : EuclideanSpace ℝ (Fin n)) (c l : Fin m → ℝ) (hc : ∀ i, 0 ≤ c i)
(I : Finset (Fin m)) (xStar : Fin m → ℝ) (hx : ∀ j, j ∉ I → xStar j = 0)
(hl : ∀ j, j ∉ I → ‖aTilde j - a j‖ ≤ l j) (hI : ∀ i, i ∈ I → aTilde i = a i) :
robustObjective a b (enlargedSet c l I) xStar = robustObjective a b (RobustRegLasso.FeatureWise.uncertaintySet c) xStar ∧
robustObjective a b (RobustRegLasso.FeatureWise.uncertaintySet c) xStar =
robustObjective aTilde b (RobustRegLasso.FeatureWise.uncertaintySet c) xStar ∧
robustObjective aTilde b (enlargedSet c l I) xStar =
robustObjective a b (RobustRegLasso.FeatureWise.uncertaintySet c) xStar := by sorry
end RobustRegLasso.Sparsity
Confirmed by the mission captain (proposal self-audit).
Confirmed by the moderator at approval.