TheoremBase

Talagrand's Inequality in the Noise Norm for a Diagonal Gaussian Reference Measure on a Hilbert Space

When the reference measure is a diagonal Gaussian whose variances are dominated by a constant multiple of the noise weights, every probability measure of finite relative entropy is noise-connected to it, and its squared noise Wasserstein distance to it is at most twice that constant times the relative entropy.

Statement

In the setting of Probability Measures on a Hilbert Space Transported in the Noise Norm: Standing Notation, let cc be a variance sequence and suppose that the reference measure is ρ=γc\rho=\gamma_{c}, the diagonal Gaussian measure on XX with variances cc, which is admissible since γc∈P2(X)\gamma_{c}\in\mathcal{P}_{2}(X) by Moments of a Diagonal Gaussian Measure on a Hilbert Space: Coordinate Covariances, Finite Second Moment, and Exponential Moments of the Squared Norm §moment. Let κ\kappa be a positive real number with ck≤κ akc_{k}\le\kappa\,a_{k} for every k∈Nk\in\mathbb{N}, where aa is the sequence of noise weights. Let μ∈P(X)\mu\in\mathcal{P}(X) have finite relative entropy H(μ ∣ γc)H(\mu\,|\,\gamma_{c}) with respect to γc\gamma_{c}. Let Pρa\mathcal{P}^{a}_{\rho} be the set of measures noise-connected to ρ\rho and WaW_{a} the noise Wasserstein distance.

1. (Noise-connected) μ∈Pρa\mu\in\mathcal{P}^{a}_{\rho}.

2. (Talagrand's inequality) The distance Wa(μ,γc)W_{a}(\mu,\gamma_{c}), defined by claim 1, satisfies

Wa(μ,γc)2≤2κ H(μ ∣ γc).W_{a}(\mu,\gamma_{c})^{2}\le2\kappa\,H(\mu\,|\,\gamma_{c}).

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…