TheoremBase

The Gaussian Entropy Pair is a Noise Penalty Pair, with Nonnegative Penalty and Dense Score Domain

The Gaussian entropy pair is a noise penalty pair: its penalty is nonnegative and measures of finite weighted Fisher information are dense among measures of finite relative entropy in the noise Wasserstein distance.

Statement

In the setting of A Diagonal Gaussian Reference Measure on the Noise Wasserstein Space, Rescaled Heads and Gaussian Tails: Standing Notation, so that the reference measure is ρ=γc\rho=\gamma_{c}, let β\beta and κ\kappa be positive real numbers with ck≤κ akc_{k}\le\kappa\,a_{k} for every k∈Nk\in\mathbb{N}, and let (D,DΣ,E,Σ)(\mathcal{D},\mathcal{D}_{\Sigma},\mathcal{E},\Sigma) be the Gaussian entropy pair with temperature β\beta, whose hypothesis holds with this κ\kappa. Noise penalty pairs on Pρa\mathcal{P}^{a}_{\rho} are those of that definition.

1. (Nonnegative penalty) 0≤E(μ)0\le\mathcal{E}(\mu) for every μ∈D\mu\in\mathcal{D}.

2. (Density of the score domain) For every μ∈D\mu\in\mathcal{D} and every positive ε∈R\varepsilon\in\mathbb{R} there is ν∈DΣ\nu\in\mathcal{D}_{\Sigma} with Wa(ν,μ)<εW_{a}(\nu,\mu)<\varepsilon.

3. (Noise penalty pair) (D,DΣ,E,Σ)(\mathcal{D},\mathcal{D}_{\Sigma},\mathcal{E},\Sigma) is a noise penalty pair on Pρa\mathcal{P}^{a}_{\rho}.

Proofs

Log in to submit a proof.

Loading...

Citations

Loading…

Dependencies

Loading…

Related

0 relations

Curated associations between results. These are editable and subjective — they do not replace the dependency graph, which is derived from the references in the text.

No relations recorded yet.

Comments

Log in to comment.

Loading…