A methodology is developed to assign, from an observed sample, a joint-probability distribution to a set of continuous variables. The algorithm proposed performs this assignment by mapping the original variables onto a jointly-Gaussian set. The map is built iteratively, ascending the log-likelihood of the observations, through a series of steps that move the marginal distributions along a random set of orthogonal directions towards normality.
"Density estimation by dual ascent of the log-likelihood." Commun. Math. Sci. 8 (1) 217 - 233, March 2010.