Theorem 2, C2 — Concentration of the discriminative Gaussian approximation
ProvedDKFAsymptotics.C2Let the state dimension be positive and finite. Let be real and let be symmetric positive-definite matrices with . Set and .
Let be probability densities and let be Gaussian probability densities with positive-definite covariances, for each positive integer . Assume the normalized density is well defined for every . Let be an arbitrary probability measure and . Assume
All densities and distances use Lebesgue measure. Weak convergence means convergence against every bounded continuous real test function. The approximate update is the specific expression ; its validity is not assumed at every index.
Then .
import Definitions.Def_DKFAsymptotics_Assumptions noncomputable section open MeasureTheory Filter Matrix open scoped Topology ENNReal
namespace DKFAsymptotics
theorem C2 {d : ℕ} [NeZero d] (M : Model d) (D : Problem M)
(h : Assumptions M D) :
Weakly D.u' (Measure.dirac D.b) := by sorry
end DKFAsymptoticsRead-back
What the Lean code literally says, in plain math · GPT-6 (Codex independent sub-agent)
C2 — independent read-back
For every positive integer dimension (so is excluded), identify the state space with , equipped with its usual topology and Lebesgue measure . Let be real matrices such that and are symmetric positive definite, meaning and for every nonzero , and suppose ; no positive-definiteness or symmetry condition is imposed on . For a vector and a symmetric positive-definite matrix , put . Let be four sequences of real-valued functions indexed by the positive integers , let , and let be a Borel probability measure on . For every positive integer , assume that each of the four functions is nonnegative -almost everywhere, is Lebesgue integrable, and has integral ; in addition, assume that there exist vectors and symmetric positive-definite real matrices such that and -almost everywhere. For any real-valued function define its associated measure, on each Borel set , by , interpreted as a nonnegative extended-real integral, and define using the nonnegative extended-real integral. Define and . Assume for every positive integer that agrees -almost everywhere with a strongly measurable real-valued function and that . Define , where is the finite positive real number represented by the extended-real value . All real-valued integrals here have the Lebesgue–Bochner convention that a nonintegrable integrand has integral zero, including the integral defining at any such point . Suppose the following five conditions hold as through the positive integers: (1) for every bounded continuous function , ; (2) in the usual topology of ; (3) for every bounded continuous real-valued , ; (4) in the usual topology of ; and (5) for every bounded continuous real-valued , . Then for every bounded continuous function , as through the positive integers; equivalently, the measures obtained from by the specified nonnegative-part density construction converge against every bounded continuous real-valued test function to the Dirac probability measure at . The sequences have no term at index , and their density and Gaussian equalities impose only almost-everywhere conditions, allowing arbitrary values on Lebesgue-null sets subject to the stated conditions on .
Confirmed by the mission captain (proposal self-audit).