Strong Converse Bounds for Compression of Mixed States
Abstract: In this paper, we study strong converse properties for both visible and blind compression of mixed states. The optimal rate of a visible compression scheme is obtained in terms of the entanglement of purification, whose additivity remains unknown so far. For a variation of extendible states, we prove that the entanglement of purification is additive and apply this to obtain a "pretty strong" converse bound for the blind and visible compression of such states. Namely, when the rate decreases below the optimal rate, the error exhibits a discontinuous jump from 0 to at least $\frac{1}{3\sqrt{2}}$. To deal with the visible case for general states, we define a new quantity $E_{\alpha,p}(A:R){\rho}$ for a bipartite state $\rho{AR}$ and $\alpha \in (0,1)\cup (1,\infty)$ as the $\alpha$-R\'enyi generalization of the entanglement of purification $E{p}(A:R){\rho}$. For $\alpha=1$, we define $E{1,p}(A:R){\rho}:=E{p}(A:R){\rho}$. We show that for any rate below the regularization $\lim{\alpha \to 1+}E_{\alpha,p}{\infty}(A:R){\rho}:=\lim{\alpha \to 1+} \lim_{n \to \infty} \frac{E_{\alpha,p}(An:Rn)_{\rho{\otimes n}}}{n}$ the fidelity for the visible compression exponentially converges to zero. Moreover, we consider blind compression of a general mixed-state source $\rho{AR}$ shared between an encoder and an inaccessible reference system $R$. We obtain a strong converse bound for the compression of this source by assuming that the decoder is a super-unital channel. This immediately implies a strong converse for the blind compression of ensembles of mixed states, by assuming a super-unital decoder, as this is a special case of the general mixed-state source $\rho{AR}$ where the reference system $R$ has a classical structure.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.