2000 character limit reached
SYMBA: Symbolic Computation of Squared Amplitudes in High Energy Physics with Machine Learning
Published 17 Jun 2022 in hep-ph and cs.LG | (2206.08901v2)
Abstract: The cross section is one of the most important physical quantities in high-energy physics and the most time consuming to compute. While machine learning has proven to be highly successful in numerical calculations in high-energy physics, analytical calculations using machine learning are still in their infancy. In this work, we use a sequence-to-sequence model, specifically, a transformer, to compute a key element of the cross section calculation, namely, the squared amplitude of an interaction. We show that a transformer model is able to predict correctly 97.6% and 99% of squared amplitudes of QCD and QED processes, respectively, at a speed that is up to orders of magnitude faster than current symbolic computation frameworks. We discuss the performance of the current model, its limitations and possible future directions for this work.
- Kim Albertsson et al. Machine learning in high energy physics community white paper. 7 2018. URL https://arxiv.org/abs/1807.02876.
- Dimitri Bourilkov. Machine and deep learning applications in particle physics. International Journal of Modern Physics A, 34(35):1930019, dec 2019. doi:10.1142/s0217751x19300199. URL https://arxiv.org/abs/1912.08245v1.
- Machine learning and the physical sciences. Reviews of Modern Physics, 91(4), Dec 2019. ISSN 1539-0756. doi:10.1103/revmodphys.91.045002. URL http://dx.doi.org/10.1103/RevModPhys.91.045002.
- A living review of machine learning for particle physics. 2 2021. doi:10.48550/arxiv.2102.02770. URL https://arxiv.org/abs/2102.02770.
- Back to the formula – lhc edition. 9 2021. URL http://arxiv.org/abs/2109.10414.
- Feyncalc 9.3: New features and improvements. Computer Physics Communications, 256:107478, 2020. ISSN 0010-4655. doi:https://doi.org/10.1016/j.cpc.2020.107478. URL https://www.sciencedirect.com/science/article/pii/S001046552030223X.
- – modern artificial theoretical physicist a c++ framework automating theoretical calculations beyond the standard model. Computer Physics Communications, 264:107928, 2021. ISSN 0010-4655. doi:https://doi.org/10.1016/j.cpc.2021.107928. URL https://www.sciencedirect.com/science/article/pii/S001046552100062X.
- Attention is all you need. 6 2017. URL https://arxiv.org/abs/1706.03762.
- CompHEP 4.4: Automatic computations from Lagrangians to events. Nucl. Instrum. Meth. A, 534:250–259, 2004. doi:10.1016/j.nima.2004.07.096.
- Scaling neural machine translation, 2018. URL https://arxiv.org/abs/1806.00187.
- Survey on automatic text summarization and transformer models applicability. In 2020 International Conference on Control, Robotics and Intelligent System, CCRIS 2020, page 176–184, New York, NY, USA, 2020. Association for Computing Machinery. ISBN 9781450388054. doi:10.1145/3437802.3437832. URL https://doi.org/10.1145/3437802.3437832.
- CPTR: full transformer network for image captioning. CoRR, abs/2101.10804, 2021. URL https://arxiv.org/abs/2101.10804.
- Bert: Pre-training of deep bidirectional transformers for language understanding, 2018. URL https://arxiv.org/abs/1810.04805.
- Andrej Karpathy and Li Fei-Fei. Deep visual-semantic alignments for generating image descriptions, 2014. URL https://arxiv.org/abs/1412.2306.
- Behrt: Transformer for electronic health records, 2019. URL https://arxiv.org/abs/1907.09538.
- Unetr: Transformers for 3d medical image segmentation, 2021. URL https://arxiv.org/abs/2103.10504.
- Dnabert: pre-trained bidirectional encoder representations from transformers model for dna-language in genome. bioRxiv, 2020. doi:10.1101/2020.09.17.301879. URL https://www.biorxiv.org/content/early/2020/09/19/2020.09.17.301879.
- Deep learning for symbolic mathematics. 12 2019. doi:10.48550/arxiv.1912.01412. URL https://arxiv.org/abs/1912.01412.
- Deep symbolic regression for recurrent sequences, 2022. URL https://arxiv.org/abs/2201.04600.
- Symbolicgpt: A generative transformer model for symbolic regression. 6 2021. URL http://arxiv.org/abs/2106.14131.
- Learning symbolic physics with graph networks. 9 2019. URL https://arxiv.org/abs/1909.05862.
- Rediscovering orbital mechanics with machine learning. 2 2022. URL http://arxiv.org/abs/2202.02306.
- Ai feynman: a physics-inspired method for symbolic regression. 5 2019. URL http://arxiv.org/abs/1905.11481.
- D. Goldberg. The standard model in a Nutshell. Princeton University Press, 2017. ISBN 9780691167596.
- Sympy: symbolic computing in python. PeerJ Computer Science, 3:e103, January 2017. ISSN 2376-5992. doi:10.7717/peerj-cs.103. URL https://doi.org/10.7717/peerj-cs.103.
- MartÃn Abadi et al. TensorFlow: Large-scale machine learning on heterogeneous systems, 2015. URL https://www.tensorflow.org/. Software available from tensorflow.org.
- Francois Chollet et al. Keras, 2015. URL https://github.com/fchollet/keras.
- Adam: A method for stochastic optimization, 2014. URL https://arxiv.org/abs/1412.6980.
- Big bird: Transformers for longer sequences. 2020. doi:10.48550/ARXIV.2007.14062. URL https://arxiv.org/abs/2007.14062.
- Longformer: The long-document transformer, 2020. URL https://arxiv.org/abs/2004.05150.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.