Theorem 7.17 / Corollary 7.18: for a target process with a location parameter and a conjugate prior with location parameter x̄, ν(x̄, n, T) = ν(x̄ − T, n, 0)
ProvedAllocationIndices.target_location_invarianceTheorem 7.17 / Corollary 7.18. If the parameter for the family of distributions for a target process is a location parameter, the sample mean is a sufficient statistic, and has a conjugate prior distribution with parameters and as in Corollary 7.10, then .
Formally: for a sampling model on with parameters , conjugate for , likelihood with location parameter , prior family with location parameter , update meanUpdate, and : the Gittins index of the target process with target in the state equals the Gittins index of the target process with target in the state . (The book's first conclusion, for the expected number of samples against a standard target process, is not restated.)
Admissible parameters. Conjugacy is required, and the conclusion stated, for only (IsConjugateOn {p | 0 < p.2}, 0 < n): a proper prior has , the book's being the improper prior of the theorem itself. Conjugacy at every cannot hold together with a location parameter. At the update divides by zero (Lean's value is ), so every observation leads to the same state . Conjugacy would then force the posterior of the prior to be the prior for every , but by the location structure that posterior moves with . Stated with conjugacy over all of , the theorem had no instances.
import Definitions.Def_AllocationIndices_Sampling open MeasureTheory ProbabilityTheory BanditAlgorithm
namespace AllocationIndices
/-- **Theorem 7.17 / Corollary 7.18** (p. 194). If the parameter `μ` of the distributions of a
target process is a location parameter, the sample mean is a sufficient statistic, and `μ` has a
conjugate prior distribution with parameters `x̄` and `n` as in Corollary 7.10, then
`ν(x̄, n, T) = ν(x̄ − T, n, 0)`: the index of the target process with target `T` in the state
`(x̄, n)` equals the index of the target process with target `0` in the state `(x̄ − T, n)`. -/
theorem target_location_invariance (F : SamplingModel ℝ (ℝ × ℝ))
(hconj : F.IsConjugateOn {p | 0 < p.2})
(hlik : HasLocationParameter F.likelihood) (hprior : PriorHasLocationParameter F.prior)
(hupd : F.update = meanUpdate) {a : ℝ} (ha0 : 0 < a) (ha1 : a < 1) (xb n T : ℝ)
(hn : 0 < n) :
gittinsIndex (F.targetChain T) (F.targetReward T) a (Sum.inl (xb, n)) =
gittinsIndex (F.targetChain 0) (F.targetReward 0) a (Sum.inl (xb - T, n)) := by sorry
end AllocationIndices
Confirmed by the mission captain (proposal self-audit).
Confirmed by the moderator at approval.