Binning-Free Unfolding Based on Monte Carlo Migration

An experimental data sample is compared to a Monte Carlo sample in the observation space. The Monte Carlo events migrate in the true variate space until the two observed samples coincide. The agreement is quantied using a Gaussian or logarithmic weight for the distance of the observations. The approach is binning-free and especially powerful in multidimensional applications where unfolding of histograms suers from the \curse of dimensionality". The study is preliminary.