Proof of Theorem 4.2, p. 13 — under Assumption 4.1, the optimal values of (10) and (12f) coincide
ProvedWassDDRO.Reduction.worstCase_eq_program12fconvex-reformulationdistributionally-robust-optimizationp2o-batch-pfp2ap2o-gran-per-chapterp2o-plan-paperp2o-v1wasserstein
Let , , and samples be as in Theorem 4.2 (, each measurable), and suppose Assumption 4.1 holds. Then for every
This is the reduction of the infinite-dimensional worst-case expectation problem to the finite convex program (12f); Theorem 4.4 (worst-case distributions) is built on it.
Formalization Note is encoded as .
Preamble
import Mathlib import Definitions.Def_WassDDRO_Reduction_Setting open MeasureTheory Filter Topology
Formal statement
namespace WassDDRO.Reduction
/-- Proof of Theorem 4.2, p. 13: under Assumption 4.1, for any `ε ≥ 0` the optimal values of
(10) and (12f) coincide. -/
theorem worstCase_eq_program12f {E : Type*} [NormedAddCommGroup E] [NormedSpace ℝ E] [FiniteDimensional ℝ E]
[MeasurableSpace E] [BorelSpace E]
{K N : ℕ} (hK : 0 < K) (hN : 0 < N) (Ξ : Set E) (ℓ : Fin K → E → EReal)
(hmeas : ∀ k, Measurable (ℓ k)) (ξhat : Fin N → E) (hξ : ∀ i, ξhat i ∈ Ξ)
(ε : ℝ) (hε : 0 ≤ ε) (hA : Assumption41 Ξ ℓ) :
worstCaseExpectation ε Ξ ξhat (maxLoss ℓ) = program12fValue ε Ξ ξhat ℓ := by sorry
end WassDDRO.Reduction
Source
Mohajerin Esfahani & Kuhn, arXiv:1505.05116v3, proof of Theorem 4.2, p. 13 ("Thus, the optimal values of (10) and (12f) coincide.")
Human review
Confirmed by the mission captain (proposal self-audit).
Confirmed by the moderator at approval.