Deep learning as a parton shower
We make the connection between certain deep learning architectures and the renormalisation group explicit in the context of QCD by using a deep learning network to construct a toy parton shower model. The model aims to describe proton-proton collisions at the Large Hadron Collider. A convolutional autoencoder learns a set of kernels that efficiently encode the behaviour of fully showered QCD collision events. The network is structured recursively so as to ensure self-similarity, and the number of trained network parameters is low. Randomness is introduced via a novel custom masking layer, which also preserves existing parton splittings by using layer-skipping connections. By applying a shower merging procedure, the network can be evaluated on unshowered events produced by a matrix element calculation. The trained network behaves as a parton shower that qualitatively reproduces jet-based observables.
KeywordsPhenomenological Models Jets
This article is distributed under the terms of the Creative Commons Attribution License (CC-BY 4.0), which permits any use, distribution and reproduction in any medium, provided the original author(s) and source are credited.
- P. Mehta and D.J. Schwab, An exact mapping between the Variational Renormalization Group and Deep Learning, arXiv:1410.3831.
- C. Bény, Deep learning and the renormalization group, arXiv:1301.3124.
- D. Oprisa and P. Toth, Criticality & Deep Learning II: Momentum Renormalisation Group, arXiv:1705.11023.
- F. Chollet et al., Keras, (2015) https://keras.io.
- J. Monk, APEMEN. Autoencoding Parton Emitting Model Encoded in Networks, (2018) https://github.com/twoev/APEMEN.
- T. Dozat, Incorporating Nesterov Momentum into Adam, in proceedings of the International Conference on Learning Representations 2016 (ICLR 2016), Caribe Hilton, San Juan, Puerto Rico, 2-4 May 2016.Google Scholar
- X. Glorot and Y. Bengio, Understanding the difficulty of training deep feedforward neural networks, in proceedings of Thirteenth International Conference on Artificial Intelligence and Statistics (AISTATS 2010), Chia Laguna Resort, Sardinia, Italy, 13-15 May 2010, volume 9, Y.W. Teh and M. Titterington eds., PMLR (2010), pp. 249-256.Google Scholar
- S. Wolfram, Universality and complexity in cellular automata, Physica D 10 (1984) 1.Google Scholar
- W. Li, N.H. Packard and C.G. Langton, Transition phenomena in cellular automata rule space, Physica D 45 (1990) 77.Google Scholar
- G. Marchesini and B.R. Webber, Simulation of QCD Jets Including Soft Gluon Interference, Nucl. Phys. B 238 (1984) 1 [INSPIRE].
- G. Marchesini and B.R. Webber, Monte Carlo Simulation of General Hard Processes with Coherent QCD Radiation, Nucl. Phys. B 310 (1988) 461 [INSPIRE].
- M. Elbayad, L. Besacier and J. Verbeek, Pervasive Attention: 2D Convolutional Neural Networks for Sequence-to-Sequence Prediction, arXiv:1808.03867.