§4.4, p. 354 — the Gentle AdaBoost update E_w(y|x) lies in [−1, 1]
ProvedAddLogReg.Gentle.update_mem_Iccboostinggentle-adaboostp2o-batch-pfp2ap2o-gran-per-chapterp2o-plan-paperp2o-v1
Let be a probability measure on , the joint law of , let , fix , and let . The population Gentle AdaBoost increment lies in the unit interval around :
The paper contrasts this with the log-ratio update of Real AdaBoost, which can be arbitrarily large in pure regions.
Preamble
import Mathlib import Definitions.Def_AddLogReg_Gentle_Setting open MeasureTheory ProbabilityTheory
Formal statement
namespace AddLogReg.Gentle
theorem update_mem_Icc {X : Type*} [MeasurableSpace X] (ν : Measure (X × Bool))
[IsProbabilityMeasure ν] (F : X → ℝ) (x : X) :
AddLogReg.ExpCrit.wCondExp ν F (fun _ b => AddLogReg.ExpCrit.sgn b) x ∈ Set.Icc (-1 : ℝ) 1 := by sorry
end AddLogReg.Gentle
Source
Friedman, Hastie and Tibshirani, Additive logistic regression: a statistical view of boosting, Ann. Statist. 28 (2000), p. 354, §4.4, first paragraph
Human review
Confirmed by the mission captain (proposal self-audit).
Confirmed by the moderator at approval.