Loop amplitudes from precision networks

Evaluating loop amplitudes is a time-consuming part of LHC event generation. For diphoton production with jets we show that simple, Bayesian networks can learn such amplitudes and model their uncertainties reliably. A boosted training of the Bayesian network further improves the uncertainty estimate and the network precision in critical phase space regions. In general, boosted network training of Bayesian networks allows us to move between fit-like and interpolation-like regimes of network training.

[1]  F. Bishara,et al.  Machine learning amplitudes for faster event generation , 2019, Physical Review D.

[2]  D. Whiteson,et al.  Machine learning and LHC event generation , 2022, SciPost Physics.

[3]  F. Siegert,et al.  Accelerating Monte Carlo event generation -- rejection sampling using neural network event-weight estimates , 2021, SciPost Physics.

[4]  J. Wells,et al.  Comparing Machine Learning and Interpolation Methods for Loop-Level Calculations , 2021, 2111.14788.

[5]  D. Maître,et al.  A factorisation-aware matrix element emulator , 2021, Journal of High Energy Physics.

[6]  Simon Badger,et al.  Optimising simulations for diphoton production at hadron colliders using amplitude neural networks , 2021, Journal of High Energy Physics.

[7]  Jack Y. Araz,et al.  Combine and conquer: event reconstruction with Bayesian Ensemble Neural Networks , 2021, Journal of High Energy Physics.

[8]  G. Kasieczka,et al.  Per-object systematics using deep-learned calibration , 2020, SciPost Physics.

[9]  S. Badger,et al.  Using neural networks for efficient evaluation of high multiplicity scattering amplitudes , 2020, Journal of High Energy Physics.

[10]  H. Schulz,et al.  Event generation with normalizing flows , 2020, Physical Review D.

[11]  S. Schumann,et al.  Exploring phase space with Neural Importance Sampling , 2020, SciPost Physics.

[12]  Jennifer Thompson,et al.  Deep-learning jets with uncertainties and more , 2019, SciPost Physics.

[13]  Alex Kendall,et al.  What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision? , 2017, NIPS.

[14]  S. Borowka,et al.  Higgs Boson Pair Production in Gluon Fusion at Next-to-Leading Order with Full Top-Quark Mass Dependence. , 2016, Physical review letters.

[15]  Yarin Gal,et al.  Uncertainty in Deep Learning , 2016 .

[16]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[17]  Peter Uwer,et al.  Numerical evaluation of virtual corrections to multi-jet production in massless QCD , 2012, Comput. Phys. Commun..

[18]  M. Czakon.  Tops from light quarks : Full mass dependence at two-loops in QCD , 2008, 0803.1400.

[19]  David Mackay,et al.  Probable networks and plausible predictions - a review of practical Bayesian methods for supervised neural networks , 1995 .

[20]  S. D. Ellis,et al.  A New Monte Carlo Treatment of Multiparticle Phase Space at High-energies , 1986 .