arXiv · 2104.08291
Better Latent Spaces for Better Autoencoders
Abstract
Autoencoders as tools behind anomaly searches at the LHC have the structural problem that they only work in one direction, extracting jets with higher complexity but not the other way around. To address this, we derive classifiers from the latent space of (variational) autoencoders, specifically in Gaussian mixture and Dirichlet latent spaces. In particular, the Dirichlet setup solves the problem and improves both the performance and the interpretability of the networks.
Explore related subjects
Keep this discovery
Barry M. Dillon, Tilman Plehn, Christof Sauer, Peter Sorrenson. 2021-04-16. Better Latent Spaces for Better Autoencoders. https://doi.org/10.21468/scipostphys.11.3.061
Cite the original work for its findings. Save a collection to share your selection of sources.