Better latent spaces for better autoencoders

41Citations
Citations of this article
29Readers
Mendeley users who have this article in their library.

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.

Cite

CITATION STYLE

APA

Dillon, B. M., Plehn, T., Sauer, C., & Sorrenson, P. (2021). Better latent spaces for better autoencoders. SciPost Physics, 11(3). https://doi.org/10.21468/SCIPOSTPHYS.11.3.061

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Save time finding and organizing research with Mendeley

Sign up for free