12 papers
Neural Boltzmann Equations
Jonas Spinner, Jack Shergold
The dynamics of particles in the early universe are described by Boltzmann equations, which involve high-dimensional phase-space integrals. Classical approaches use quadrature inte…
Virtues and Vices of Equivariant Transformers
Luigi Favaro, Tilman Plehn, Huilin Qu +1
We study for the first time the benefit of Lorentz-equivariant transformers for large-size jet tagging and flavor tagging. To control their computing demands, we optimize all imple…
Forecasting Generative Amplification
Henning Bahl, Sascha Diefenbacher, Nina Elmer +2
Generative networks are perfect tools to enhance the speed and precision of LHC simulations. Especially when generating events beyond the size of the training dataset, it is import…
Economical Jet Taggers -- Equivariant, Slim, and Quantized
Antoine Petitjean, Tilman Plehn, Jonas Spinner +1
Modern machine learning is transforming jet tagging at the LHC, but the leading transformer architectures are large, not particularly fast, and training-intensive. We present a sli…
Extrapolating Jet Radiation with Autoregressive Transformers
Anja Butter, François Charton, Javier Mariño Villadamigo +3
Generative networks are an exciting tool for fast LHC event fixed number of particles. Autoregressive transformers allow us to generate events containing variable numbers of partic…
Lorentz-Equivariance without Limitations
Luigi Favaro, Gerrit Gerhartz, Fred A. Hamprecht +5
Lorentz Local Canonicalization (LLoCa) ensures exact Lorentz-equivariance for arbitrary neural networks with minimal computational overhead. For the LHC, it equivariantly predicts…