Uncertainty-Aware Multidimensional Scaling (UAMDS) is a dimensionality reduction method for uncertain data. The paper publication titled "Uncertainty-Aware Multidimensional Scaling" by David Hägele, Tim Krake, and Daniel Weiskopf, is available at https://doi.org/10.1109/TVCG.2022.3209420 (open access, best paper at IEEE VIS 2022).

To model the uncertainty of each element in a dataset, an element is no longer expressed as a vector, but as a random vector with its own multivariate probability distribution. So instead of reducing a set of high-dimensional data points to low-dimensional points