# Is There an Optimal Bandwidth for Kernel Density Estimation at One Point

I am trying to estimate the density of a 2D distribution using KDE, but I only care about the accuracy right at the origin. I have read about methods to estimate the optimal bandwidth matrix when you want to minimize the mean integrated squared error (or other metrics that try to estimate the error over the full distribution). I want to know if there are equivalent methods that are optimal in terms of minimizing the error at a single point.