Generating CPD tensor factors instead of full tensors inside GANs and diffusion models can cut output parameters by roughly 80-90% while keeping similar FID scores on calorimeter data.
Fast simulation of a high granularity calorimeter by generative adversarial networks
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
support 1representative citing papers
citing papers explorer
-
Efficiently Generating Multidimensional Calorimeter Data with Tensor Decomposition Parameterization
Generating CPD tensor factors instead of full tensors inside GANs and diffusion models can cut output parameters by roughly 80-90% while keeping similar FID scores on calorimeter data.