Gaussian four-point function (eq. 1.44)
ProvedDeepLearningTheory.gaussian_four_pointLet be a symmetric positive-definite real matrix and let follow the zero-mean Gaussian distribution with covariance . For all indices ,
This is the case of Wick's theorem, with three pairings.
import Mathlib import Definitions.Def_DLT_GaussianIntegrals open MeasureTheory
namespace DeepLearningTheory
theorem gaussian_four_point {N : ℕ} (K : Matrix (Fin N) (Fin N) ℝ) (hK : K.PosDef)
(μ₁ μ₂ μ₃ μ₄ : Fin N) :
gaussExpect K (fun z => z μ₁ * z μ₂ * z μ₃ * z μ₄)
= K μ₁ μ₂ * K μ₃ μ₄ + K μ₁ μ₃ * K μ₂ μ₄ + K μ₁ μ₄ * K μ₂ μ₃ := by sorry
end DeepLearningTheoryRead-back
What the Lean code literally says, in plain math · Aristotle (Harmonic) - non-blind, same agent as the drafter
Non-blind read-back. This read-back was written by the same agent that drafted the Lean statement, with full knowledge of the source text and of the intended meaning. It is not independent testimony and must not be mistaken for a blind audit; reviewers should compare the Lean code against the source themselves.
For every , every positive-definite real matrix and all (not necessarily distinct): , with the density and the integral a Bochner integral against Lebesgue measure.
Confirmed by the mission captain (proposal self-audit).
Confirmed by the moderator at approval.