A quick announcement that my advisor and I have posted an update to our paper, “Behavior of The Maximum Likelihood in State Tomography”, on the arXiv.
Relative to the previous version, we have added new technical content, including a generalization of Local Asymptotic Normality that is applicable to models with convex boundaries. This generalization allows us to prove several useful results about the loglikelihood ratio statistic, including that it is related to squared error. (A property we had taken for granted in the previous version.) In addition, we provide a more accurate formula for its expected value.
I encourage you to check it out! If you have any comments or questions, feel free to email me or open an issue on the GitHub repository.