Klein–Rio Lemma 4.5: upper bound on the compensation function
ProvedTalagrandCore.lemma45_upperconcentration-inequalitiesempirical-processesprobabilitytalagrand
Define and . For ,
This analytic estimate controls the coefficient in the compensated-process differential inequality.
Formalization Note This is the upper half of Klein–Rio Lemma 4.5 in the exact scalar form used downstream.
Preamble
import Definitions.Def_talagrand_finite_bool_core open MeasureTheory open scoped Classical BigOperators
Formal statement
namespace TalagrandCore
variable {κ ι : Type} [DecidableEq κ] [Fintype κ]
variable [Fintype ι] [Nonempty ι]
theorem lemma45_upper (t : ℝ) (ht0 : 0 ≤ t) (ht : t ≤ 1/2) :
phiKR t ≤ t * Real.exp (2*t) - t^2/2 := by sorry
end TalagrandCoreSource
T. Klein and E. Rio, Concentration around the mean for maxima of empirical processes, Annals of Probability 33 (2005), Sections 2 and 4, pp. 1060–1077, arXiv:math/0506594. Formal Lean proof extracted from Prove2Me accepted submission bf106d23-ff42-48f5-a837-a8528101c849 by tianyipeng.