Speaker
Jack Collins
(SLAC)
Description
Variational Autoencoders (VAEs) can be trained to learn representations of metric spaces. I will show how a VAE trained to minimize the Earth Movers Distance (EMD) between input and reconstructed jets learns to represent jet features associated with hierarchically different energy scales in orthogonal directions of its latent space. I will also illustrate the relationship between the scale-dependent dimensionality of the learnt representation and the dimensionality of the metric space.
Primary author
Jack Collins
(SLAC)
