Orateur
Gregor Kasieczka
(Universität Hamburg)
Description
Recent progress in generative models allows the unsupervised learning and interpolation of high-dimensional distributions. This, for example, makes possible approaches for anomaly detection based on weak supervision by first interpolating into a region with potential signal present, and then training a classifier to find such a potential signal. This lecture and tutorial will introduce the necessary ingredients based on hands-on examples and discuss current challenges and progress.
