Guaranteed recovery of a low-rank and joint-sparse matrix from incomplete and noisy measurements

Assume a multichannel data matrix, which due to the column-wise dependencies, has low-rank and joint-sparse representation. This matrix wont have many degrees of freedom. Enormous developments over the last decade in areas of compressed sensing and low-rank matrix recovery, let us thinking of acquiring the whole matrix elements from very few non-adaptive linear measurements. This paper attempts to answer the following questions: what should be those measurements? How to design a computationally tractable algorithm to recover data from noisy measurements? Finally, how the recovery method performs, and is it stable for approximately low-rank or not exactly joint-sparse matrices?