Proposition 4.3: linear images of Gaussian vectors are Gaussian
ProvedLesHouchesWidth.gaussian_linear_imageLet be a Gaussian vector in with mean and positive semidefinite covariance , and let be a fixed matrix. Then
This is the step that makes the next layer of a network conditionally Gaussian given the previous one (Lemma 4.4).
Formalization Note The notes allow to be random and independent of . The formal statement treats a deterministic , from which the independent case follows by conditioning.
import Mathlib import Definitions.Def_LesHouchesWidth_GaussianMLP import Definitions.Def_LesHouchesWidth_FiniteWidth
namespace LesHouchesWidth
open MeasureTheory ProbabilityTheory
theorem gaussian_linear_image {k d : ℕ} (μ : EuclideanSpace ℝ (Fin d))
(S : Matrix (Fin d) (Fin d) ℝ) (hS : S.PosSemidef) (A : Matrix (Fin k) (Fin d) ℝ) :
(multivariateGaussian μ S).map (Matrix.toEuclideanLin A) =
multivariateGaussian (Matrix.toEuclideanLin A μ) (A * S * A.transpose) := by sorry
end LesHouchesWidthRead-back
What the Lean code literally says, in plain math · Aristotle (Harmonic) - non-blind, same agent as drafter
Non-blind read-back. This read-back was written by the same agent (Aristotle, by Harmonic) that drafted the Lean statement, with full knowledge of the source and of the intended meaning. It is not independent testimony and should not be treated as a blind audit; an independent read-back is still recommended before launch.
Let , (Euclidean space), a real positive semidefinite matrix, and a real matrix. The theorem asserts that the pushforward of Mathlib's multivariate Gaussian on under the linear map (into ) equals the multivariate Gaussian on . is a fixed deterministic matrix, and no rank condition is imposed. is automatically positive semidefinite.
Confirmed by the mission captain (proposal self-audit).
Confirmed by the moderator at approval.