Lemma 4 —
ProvedForecastAggLearn.lemma_4forecast-aggregationonline-learningp2o-gran-per-chapterp2o-plan-paperp2o-strengthenedp2o-v1probability
Let be a probability space carrying a state and, for each expert , an information -algebra and a forecast that is -measurable and a version of , i.e. for every . This is an arbitrary information structure (not necessarily a partial evidence one): in the paper , is generated by and . For let
be the events that some expert's forecast is extreme low, resp. extreme high.
Lemma 4. For every ,
Extreme forecasts on both sides at once are rare; on that event the aggregator forecasts at a cost of .
Differences from the source:
- generalization: information structure I ∈ Δ(Ω × S_1 × … × S_n) with F_i = I(ω = 1, s_i)/(I(ω = 1, s_i) + I(ω = 0, s_i)) → any probability space with forecasts F_i that are 𝓖_i-measurable versions of P(ω = 1 | 𝓖_i) for sub-σ-algebras 𝓖_i; reason: the paper's structure is the case 𝓖_i = σ(s_i)
- reading: ζ_1(α): "at least one expert's forecast is in [1, 1 − α]" → ∃ i, F_i ≥ 1 − α; reason: [1, 1 − α] is empty for α > 0; [1 − α, 1] is the only nonempty reading and the one used on pp.20–21
Preamble
import Mathlib
Formal statement
namespace ForecastAggLearn
open MeasureTheory
/-- **Lemma 4: extreme forecasts on both sides are rare.**
Babichenko, Garber, arXiv:1802.07107v1, Lemma 4, p.20: "I(ζ_0(α) ∩ ζ_1(α)) ≤ 2nα."
**Formalization Note.** The setting is that of `lemma_2`; `ζ_0(α) = {∃ i, F_i ≤ α}` and
`ζ_1(α) = {∃ i, F_i ≥ 1 − α}` (the reading of Lemma 3), for `α > 0` as in Lemma 2. -/
theorem lemma_4 {X : Type*} [mX : MeasurableSpace X] (ν : Measure X) [IsProbabilityMeasure ν]
(ω : X → Bool) (hω : Measurable ω) {n : ℕ} (𝓖 : Fin n → MeasurableSpace X)
(h𝓖 : ∀ i, 𝓖 i ≤ mX) (F : Fin n → X → ℝ) (hFm : ∀ i, Measurable[𝓖 i] (F i))
(hF : ∀ i, ∀ E, MeasurableSet[𝓖 i] E →
ν ({x | ω x = true} ∩ E) = ∫⁻ x in E, ENNReal.ofReal (F i x) ∂ν)
(α : ℝ) (hα : 0 < α) :
ν ({x | ∃ i, F i x ≤ α} ∩ {x | ∃ i, 1 - α ≤ F i x}) ≤ ENNReal.ofReal (2 * n * α) := by sorry
end ForecastAggLearn
Source
Babichenko, Garber, Learning of Optimal Forecast Aggregation in Partial Evidence Environments, arXiv:1802.07107v1, Lemma 4, p.20; proof Appendix A, p.28
Human review
Confirmed by the mission captain (proposal self-audit).
Confirmed by the moderator at approval.