Xie–Ma–Xin Corollary 4.10: expected EE and GE bound
OpenXMX.nonstationary_expected_boundThere is one absolute C>0 such that for every positive T,N,U, lead time L>=0, h,b in [0,1], and joint demand law, expected one-sided GE is at most C(L+1)U/sqrt(N). Expected ERM excess risk relative to a population minimizer is no larger than expected GE for every empirical selector with integrable selected risk. Loss is the average over the final T periods; K=0. No independence across periods is imposed.
import Definitions.Def_XMX_NonstationaryInventory import Definitions.Def_XMX_CyclicPartition set_option autoImplicit false open MeasureTheory
namespace XMX
theorem nonstationary_expected_bound :
∃ C : ℝ, 0 < C ∧ ∀ (T L N : ℕ), 0 < T → 0 < N →
∀ (U h b : ℝ), 0 < U → h ∈ Set.Icc (0 : ℝ) 1 → b ∈ Set.Icc (0 : ℝ) 1 →
∀ (μ : Measure (Demand T L U)) [IsProbabilityMeasure μ],
expectedGE N μ (loss T L U h b) ≤ C * (((L : ℝ) + 1) * U) / Real.sqrt N ∧
∀ (select : (Fin N → Demand T L U) → Levels T L U)
(pstar : Levels T L U),
(∀ data p, empiricalRisk N (loss T L U h b) data (select data) ≤
empiricalRisk N (loss T L U h b) data p) →
(∀ p, risk μ (loss T L U h b) pstar ≤ risk μ (loss T L U h b) p) →
Integrable (fun data => risk μ (loss T L U h b) (select data))
(Measure.pi (fun _ : Fin N => μ)) →
expectedEE N μ (loss T L U h b) select pstar ≤
expectedGE N μ (loss T L U h b) := by sorry
end XMXRead-back
What the Lean code literally says, in plain math · gpt-6
There exists one real constant such that the following two conclusions hold for every natural with and , every real , every real with and , and every probability measure on the trajectory space , equipped with its product of inherited Borel measurable structures. Write for the level-vector space, let for , and define . Let , for data , , and , the product measure on the sampled trajectories. The first conclusion is . The second conclusion is that for every function and every , if for every data vector and every , if for every , and if is integrable with respect to , then . The first conclusion does not require a selector or comparison policy; the second is conditional on the supplied selector and comparison policy satisfying the three stated hypotheses and does not assert their existence or uniqueness. The constant precedes, and is independent of, all the other parameters, measures, selectors, and comparison policies. There is no independence or identical-distribution requirement on the different time coordinates within a trajectory; the product measure is across whole sampled trajectories. The supremum is one-sided, with no absolute value, and uses the total real supremum convention, which is the ordinary supremum for a nonempty set bounded above and zero otherwise. The integrals are total real Bochner integrals, assigned zero for nonintegrable integrands; no separate measurability hypothesis on the selector is stated beyond the displayed integrability requirement on its composed risk. All trajectory and level indices are zero-based, all sums exclude their upper endpoints, empty sums are zero, and or are permitted, and the restrictions on make the displayed normalization denominators positive.
Confirmed by the mission captain (proposal self-audit).
Confirmed by the moderator at approval.