Proof of Theorem 6, p. 34 — −log(1 − t) ≤ t + 2t² for |t| ≤ 1/2
ProvedEmpiricalDRO.Consistency.neg_log_one_sub_leelementary-inequalitylogarithmp2o-batch-pfp2ap2o-gran-per-chapterp2o-plan-paperp2o-v1
For every real with ,
In the proof of Theorem 6 (and hence of Theorem 3) this inequality, applied with , turns the dual objective (76) into the explicit upper bound (77).
Preamble
import Mathlib import Definitions.Def_EmpiricalDRO_Consistency_Setting open MeasureTheory ProbabilityTheory Filter Topology
Formal statement
namespace EmpiricalDRO.Consistency /-- The elementary inequality used in the proof of Theorem 6, Lam, arXiv:1605.09349v1, p. 34: `−log(1 − t) ≤ t + 2t²` for every `|t| ≤ 1/2`. -/ theorem neg_log_one_sub_le : ∀ t : ℝ, |t| ≤ 1 / 2 → -Real.log (1 - t) ≤ t + 2 * t ^ 2 := by sorry end EmpiricalDRO.Consistency
Source
Lam, Recovering Best Statistical Guarantees via the Empirical DRO, arXiv:1605.09349v1, p. 34, proof of Theorem 6, the sentence before (77)
Human review
Confirmed by the mission captain (proposal self-audit).
Confirmed by the moderator at approval.