Xie–Ma–Xin Theorem 4.9: normalized inventory fat-shattering bound
ProvedXMX.nonstationary_inventory_fat_boundFor every positive T,U, nonnegative integer lead time L, period k<T, and margin 0<gamma<=1, every gamma-shattered sample for the normalized inventory class has size m<=2/gamma+1. Shattering uses >tau+gamma for high labels and <=tau-gamma for low labels. This concerns the inventory class, not its loss pseudodimension.
import Definitions.Def_XMX_NonstationaryInventory import Definitions.Def_XMX_CyclicPartition set_option autoImplicit false open MeasureTheory
namespace XMX
theorem nonstationary_inventory_fat_bound
(T L : ℕ) (hT : 0 < T) (U γ : ℝ) (hU : 0 < U)
(hγ : 0 < γ) (hγ1 : γ ≤ 1) (k : ℕ) (hk : k < T)
(m : ℕ) (x : Fin m → Demand T L U) (τ : Fin m → ℝ)
(hshatter : Shatters (normalizedInventory T L U k) γ m x τ) :
(m : ℝ) ≤ 2 / γ + 1 := by sorry
end XMXRead-back
What the Lean code literally says, in plain math · gpt-6
For every positive natural number , every natural number (including zero), every real , every real with , every natural , every natural , every indexed collection of functions , and every collection of real thresholds , suppose the following holds: for every Boolean labeling of , there exists a level vector such that, for every , the quantity satisfies when and when . Then , with interpreted as a real number in this inequality. The level vector may depend on the entire labeling, and the indexed trajectories need not be distinct. All coordinates are zero-based; the sum excludes its upper endpoint and is zero when empty, including the term when . The maximum has entries, all indices used are in the stated trajectory and level domains because , and the normalization denominator is positive. The case is included.
Confirmed by the mission captain (proposal self-audit).
Confirmed by the moderator at approval.