Lemma 4 — scalar and directional Gaussian observation bias
ProvedLG2021.Concentration.parameter_observation_bias_boundsLet be positive integers and . Set
Let be -Lipschitz, with and . Let and . Draw from the standard Euclidean Gaussian, and then draw from a measurable probability kernel .
Assume that, for Gaussian-almost every , the exponential moment is integrable and at most two. On the support of the published Gaussian truncation at , assume . The conditional mean outside that support is unrestricted.
Let be the published truncated scalar likelihood-ratio coefficient, and let be its published directional gradient coefficient. For the Gaussian surrogate
both numerical bias estimates hold:
The expectations use the Gaussian/kernel joint measure.
This isolates the scalar and gradient bias bounds associated with Lemma 4(a,b) of Lattimore and György (COLT 2021, PMLR 134), using the formal proof's explicit parameter choices and a conditional observation-kernel formulation. Requiring the mean only where the truncation is active permits legal-query fallback outside the active Gaussian region. All coefficients and Gaussian objects are the existing published definitions. This node is a closed analytic ingredient in the dimension-dependent stochastic convex-bandit regret proof.
import Mathlib import Definitions.Def_LG2021_GaussianEstimators open LG2021 LG2021.Concentration MeasureTheory ProbabilityTheory
theorem LG2021.Concentration.parameter_observation_bias_bounds {d n : ℕ} (hd : 0 < d) (hn : 0 < n)
{D : ℝ} (hD : 0 ≤ D) {f : Space d → ℝ} {K : NNReal}
(hf : LipschitzWith K f) (hf0 : |f 0| ≤ 1)
(hK : (K : ℝ) ≤ paperLipschitz d D (parameterLog d D n))
(z η : Space d) (hz : ‖z‖ ≤ paperRadius d (parameterLog d D n) / (2 * (d : ℝ)))
(hη : ‖η‖ ≤ 1) (κ : Kernel (Space d) ℝ) [IsMarkovKernel κ]
(hobs : ∀ᵐ x ∂gaussian d, Integrable (fun y : ℝ => Real.exp (y ^ 2 / 16)) (κ x) ∧
(∫ y : ℝ, Real.exp (y ^ 2 / 16) ∂κ x) ≤ 2)
(hmean : ∀ᵐ x ∂gaussian d,
truncation (paperLambda d (parameterLog d D n)) (paperRadius d (parameterLog d D n)) z x = 1 →
(∫ y, y ∂κ x) = f x) :
|(∫ p : Space d × ℝ, p.2 * scalarCoefficient (paperLambda d (parameterLog d D n))
(paperRadius d (parameterLog d D n)) z p.1 ∂((gaussian d) ⊗ₘ κ)) -
surrogate (paperLambda d (parameterLog d D n)) f z| ≤
1 / (8 * paperRadius d (parameterLog d D n) * (n : ℝ)) ∧
|(∫ p : Space d × ℝ, p.2 * directionalGradientCoefficient (paperLambda d (parameterLog d D n))
(paperRadius d (parameterLog d D n)) z η p.1 ∂((gaussian d) ⊗ₘ κ)) -
fderiv ℝ (surrogate (paperLambda d (parameterLog d D n)) f) z η| ≤
1 / (8 * paperRadius d (parameterLog d D n) * (n : ℝ)) := by sorry