This #CMSPaper investigates different #AI #machinelearning methods that aim to find jets that are inconsistent with the standard model. It shows that a new method called #Wasserstein normalized autoencodes works much better than other neural networks arxiv.org/abs/2510.02168
@freyablekman I got excited and thought this was going to be using the "energy mover" Wasserstein distance on the jets themselves, which is something we're studying, but I think it's rather the metric used for similarity of the autoencoder pdfs (before I drowned in ML technicalities). Nice, though 🙃
@agbuckley so still some work left for you then, that’s also nice :-)