Winner-takes-all learners are geometry-aware conditional density estimators

arXiv:2406.04706v1 Announce Type: cross
Abstract: Winner-takes-all training is a simple learning paradigm, which handles ambiguous tasks by predicting a set of plausible hypotheses. Recently, a connection was established between Winner-takes-all training and centroidal Voronoi tessellations, showing that, once trained, hypotheses should quantize optimally the shape of the conditional distribution to predict. However, the best use of these hypotheses for uncertainty quantification is still an open question.In this work, we show how to leverage the appealing geometric properties of the Winner-takes-all …

abstract arxiv cs.lg cs.ne distribution eess.sp geometry however math.pr paradigm plausible set shape simple stat.ml tasks training type voronoi