Odd Gaussian moments vanish
ProvedDeepLearningTheory.gaussian_odd_moment_zeroLet be a symmetric positive-definite real matrix and let follow the zero-mean Gaussian distribution with covariance . For every and all indices ,
Together with Wick's theorem this determines all moments of the Gaussian.
import Mathlib import Definitions.Def_DLT_GaussianIntegrals open MeasureTheory
namespace DeepLearningTheory
theorem gaussian_odd_moment_zero {N : ℕ} (K : Matrix (Fin N) (Fin N) ℝ) (hK : K.PosDef)
(m : ℕ) (μs : Fin (2 * m + 1) → Fin N) :
gaussExpect K (fun z => ∏ a : Fin (2 * m + 1), z (μs a)) = 0 := 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 , every and every map from (so labels) to (repetitions allowed), the integral equals , where and the integral is a Bochner integral with respect to Lebesgue measure.
Confirmed by the mission captain (proposal self-audit).
Confirmed by the moderator at approval.