Theorem 5′ — an optimal supported on stays optimal for any within of off , over the enlarged set
ProvedRobustRegLasso.Sparsity.theorem_5_primeLet and radii , and let . Let be an optimal solution of the robust regression problem
and let be such that for all . For numbers let
Then for every with for and for , is an optimal solution of
This is the main theorem of the paper's Section IV: Theorem 5 is its special case with off , and through Theorem 5 it yields the incoherence-type sparsity criterion of Theorem 6.
Formalization Note The radius vector is arbitrary (not fixed), so that Theorem 5 is a specialization. The paper does not state ; it is implied by , so is left unconstrained. The radii are the paper's standing convention for (2) (with a negative radius is empty and every is vacuously optimal, so the statement would fail). "Optimal" means minimizing the EReal-valued supremum over all of ; existence of an optimal solution is assumed, not claimed. The paper's is the norm.
import Mathlib import Definitions.Def_RobustRegLasso_Sparsity_Basic
namespace RobustRegLasso.Sparsity
theorem theorem_5_prime {n m : ℕ} (a : Fin m → EuclideanSpace ℝ (Fin n))
(b : EuclideanSpace ℝ (Fin n)) (c l : Fin m → ℝ) (hc : ∀ i, 0 ≤ c i)
(xStar : Fin m → ℝ) (hopt : IsRobustSolution a b (RobustRegLasso.FeatureWise.uncertaintySet c) xStar)
(I : Finset (Fin m)) (hx : ∀ j, j ∉ I → xStar j = 0) :
∀ aTilde : Fin m → EuclideanSpace ℝ (Fin n),
(∀ j, j ∉ I → ‖aTilde j - a j‖ ≤ l j) → (∀ i, i ∈ I → aTilde i = a i) →
IsRobustSolution aTilde b (enlargedSet c l I) xStar := by sorry
end RobustRegLasso.Sparsity
Confirmed by the mission captain (proposal self-audit).
Confirmed by the moderator at approval.