7 papers
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…
Generative Unfolding of Jets and Their Substructure
Antoine Petitjean, Anja Butter, Kevin Greif +4
Unfolding, for example of distortions imparted by detectors, provides suitable and publishable representations of LHC data. Many methods for unbinned and high-dimensional unfolding…
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…
The SN 1987A Cooling Bound on Dark Matter Absorption in Electron Targets
Claudio Andrea Manzari, Jorge Martin Camalich, Jonas Spinner +1
We present new supernova (SN 1987A) cooling bounds on sub-MeV fermionic dark matter with effective couplings to electrons. These bounds probe the parameter space relevant for direc…
Lorentz Local Canonicalization: How to Make Any Network Lorentz-Equivariant
Jonas Spinner, Luigi Favaro, Peter Lippmann +4
Lorentz-equivariant neural networks are becoming the leading architectures for high-energy physics. Current implementations rely on specialized layers, limiting architectural choic…
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…