Constructing valid density matrices on an NMR quantum information processor via maximum likelihood estimation

Estimation of quantum states is one of the most important steps in any quantum information processing experiment. A naive reconstruction of the density matrix from experimental measurements can often give density matrices which are not positive, and hence not physically acceptable. How do we ensure that at all stages of reconstruction, we keep the density matrix positive and normalized? Recently a method has been suggested based on maximum likelihood estimation, wherein the density matrix is guaranteed to be positive definite. We experimentally implement this protocol and demonstrate its utility on an NMR quantum information processor. We discuss several examples where we undertake such an estimation and compare it with the standard method of state estimation.