In a recent paper http://arxiv.org/abs/1403.6102, we defined a quantity that we called the "Renyi conditional mutual information" and investigated several of its properties. We have some open conjectures, and I would like to pose them as open questions to the mathematics community on this forum. Perhaps there is a simple resolution, but we have considered known approaches and it appears that new tools are necessary for solving these problems (or maybe known tools could work?).

Background

Let denote a Hilbert space, and let denote the set of density operators acting on this Hilbert space (positive semi-definite operators with trace one). (It suffices for our purposes to consider finite-dimensional Hilbert spaces, but of course the infinite-dimensional case is interesting as well.) We are interested in "three-party" density operators acting on the tensor-product Hilbert space . Let denote the "marginal" density operator of , obtained by taking a partial trace over the spaces : In a similar way, we can define , , , , and .

We define the "Renyi conditional mutual information" of order as follows: In the above, identity operators are implicit, so that, e.g., , where is the identity operator acting on . For more motivation for the above quantity, please consult our paper.

We can easily prove that the above quantity is "monotone under a local quantum operation acting on system " for all , i.e., that the following inequality holds where , denotes the identity map, and is a completely positive trace preserving linear map acting on system . A proof follows by applying a standard approach with the Lieb concavity theorem and the Ando convexity theorem (proof is detailed in the paper).

Conjectures/Questions

We have several conjectures which (to fit the MathOverflow format) could be converted into questions in obvious ways (e.g., are the statements true? please provide an argument or counterexample, etc.).

Conjecture 1:

The quantity is "monotone under a local quantum operation acting on system " for all , i.e., the following inequality holds where and is a completely positive trace preserving linear map acting on system . (Numerical evidence indicates that this conjecture should be true.)

Conjecture 2:

The Renyi conditional mutual information of order should be monotone increasing in the Renyi parameter , i.e., if , then (Numerical evidence indicates that this conjecture should be true as well, and we furthermore have proofs that it is true in some special cases (for in a neighborhood of one and when ).)

These are the basic conjectures, but please consult our paper for more general forms of them. Solving the first conjecture would be very interesting for us, as it would establish the Renyi conditional mutual as a true "Renyi generalization" of the "von Neumann style" quantum conditional mutual information. Solving the second conjecture would have widespread implications throughout quantum information theory and even for condensed matter physics (topological order - pdf).