Squared Noise Derivative Bound for Inverse-Covariance Trace
ProvedFunctionalInequalities.KLS.BKL.Localization.sum_sq_fderiv_stdTrace_ringInverse_cov_noise_le_modularfunctional-inequalitieskls-conjecturekls-modularlog-concave
This bounds the sum of squared noise derivatives of the inverse-covariance trace.
Let be a compactly supported isotropic log-concave probability measure on , assume CumulantBoundCompact 2 8, and let have self-adjoint positive-semidefinite . Then
The result is a quantitative derivative estimate for the inverse-covariance component of the localization Lyapunov function.
Superseded upload. This snapshot was replaced by FunctionalInequalities.KLS.BKL.Localization.sum_sq_fderiv_stdTrace_ringInverse_cov_noise_le_readable: open the readable replacement. The replacement preserves the frozen source and mathematical statement, with a compact declaration context. This historical node remains available for existing imports.
Preamble
import Definitions.Def_KLSModular_FunctionalInequalities_KLS_BKL_Localization_Lyapunov_Bound
noncomputable section
section S5E1BLyapunovBound
open MeasureTheory
open scoped RealInnerProductSpace ContDiff
open FunctionalInequalities.Probability.Posterior FunctionalInequalities.Analysis
FunctionalInequalities.Analysis.BakryEmery FunctionalInequalities.Probability.Diffusion
FunctionalInequalities.Analysis.CoordinateTensor
section
namespace FunctionalInequalities
end FunctionalInequalities
open FunctionalInequalities
section
namespace FunctionalInequalities.KLS
end FunctionalInequalities.KLS
open FunctionalInequalities FunctionalInequalities.KLS
section
namespace FunctionalInequalities.KLS.BKL
end FunctionalInequalities.KLS.BKL
open FunctionalInequalities FunctionalInequalities.KLS FunctionalInequalities.KLS.BKL
section
namespace FunctionalInequalities.KLS.BKL.Localization
end FunctionalInequalities.KLS.BKL.Localization
open FunctionalInequalities FunctionalInequalities.KLS FunctionalInequalities.KLS.BKL FunctionalInequalities.KLS.BKL.Localization
variable {n : ℕ} (μ : ProbabilityMeasure (EuclideanSpace ℝ (Fin n)))
(hc : IsCompact (μ : Measure (EuclideanSpace ℝ (Fin n))).support)
set_option maxHeartbeats 1000000
Formal statement
theorem FunctionalInequalities.KLS.BKL.Localization.sum_sq_fderiv_stdTrace_ringInverse_cov_noise_le_modular (hiso : KLS.Isotropic μ) (hLC : KLS.LogConcave μ)
(h8 : LogConcave.Suspension.CumulantBoundCompact 2 8) (p : Param n)
(hSym : IsSelfAdjoint p.2) (hQ : ∀ x, 0 ≤ ⟪p.2 x, x⟫) :
∑ k, (fderiv ℝ (fun q : Param n => stdTrace (Ring.inverse (cov μ hc q))) p (noise μ hc p k)) ^ 2 ≤
8 * n * stdTrace (Ring.inverse (cov μ hc p)) ^ 2 := by sorry
Source
Lean source: https://github.com/human-ai-mathematics/kls-lean/blob/408915f/formalization/FunctionalInequalities/KLS/BKL/Localization/Lyapunov/Bound.lean#L224-L377 (repository human-ai-mathematics/kls-lean, commit 408915f, module `FunctionalInequalities.KLS.BKL.Localization.Lyapunov.Bound`, declaration `FunctionalInequalities.KLS.BKL.Localization.sum_sq_fderiv_stdTrace_ringInverse_cov_noise_le`; the repository is private at upload time).