2000 character limit reached
Fast Particle-based Anomaly Detection Algorithm with Variational Autoencoder (2311.17162v1)
Published 28 Nov 2023 in hep-ex and cs.LG
Abstract: Model-agnostic anomaly detection is one of the promising approaches in the search for new beyond the standard model physics. In this paper, we present Set-VAE, a particle-based variational autoencoder (VAE) anomaly detection algorithm. We demonstrate a 2x signal efficiency gain compared with traditional subjettiness-based jet selection. Furthermore, with an eye to the future deployment to trigger systems, we propose the CLIP-VAE, which reduces the inference-time cost of anomaly detection by using the KL-divergence loss as the anomaly score, resulting in a 2x acceleration in latency and reducing the caching requirement.
- A Tapper and Darin Acosta. CMS Technical Design Report for the Level-1 Trigger Upgrade. Technical report, 2013. Additional contacts: Jeffrey Spalding, Fermilab, [email protected] Didier Contardo, Universite Claude Bernard-Lyon I, [email protected].
- CMS High Level Trigger. Technical report, CERN, Geneva, 2007. revised version submitted on 2007-10-19 16:57:09.
- The level-1 global trigger for the cms experiment at lhc. Journal of Instrumentation, 2(01):P01006, 2007.
- Observation of a new boson at a mass of 125 gev with the cms experiment at the lhc. Physics Letters B, 716(1):30–61, 2012.
- Anomaly detection with density estimation. Physical Review D, 101(7):075042, 2020.
- Deep learning for anomaly detection: A review. ACM computing surveys (CSUR), 54(2):1–38, 2021.
- Qcd or what? SciPost Physics, 6(3):030, 2019.
- Autoencoders on field-programmable gate arrays for real-time, unsupervised new physics detection at 40 mhz at the large hadron collider. Nature Machine Intelligence, 4(2):154–161, 2022.
- Bryan Ostdiek. Deep set auto encoders for anomaly detection in particle physics. SciPost Physics, 12(1):045, 2022.
- Lorentz group equivariant autoencoders. The European Physical Journal C, 83(6):485, 2023.
- Javier Duarte et al. Fast inference of deep neural networks in FPGAs for particle physics. JINST, 13(07):P07027, 2018.
- The lhc olympics 2020 a community challenge for anomaly detection in high energy physics. Reports on progress in physics, 84(12):124201, 2021.
- Searching for new physics with deep autoencoders (2018). arXiv preprint arXiv:1808.08992.
- Anomaly detection with convolutional graph neural networks. Journal of High Energy Physics, 2021(8):1–19, 2021.
- Autoencoders for unsupervised anomaly detection in high energy physics. Journal of High Energy Physics, 2021(6):1–32, 2021.
- Deep sets. Advances in neural information processing systems, 30, 2017.
- Permutation equivariant layers for higher order interactions. In Gustau Camps-Valls, Francisco J. R. Ruiz, and Isabel Valera, editors, Proceedings of The 25th International Conference on Artificial Intelligence and Statistics, volume 151 of Proceedings of Machine Learning Research, pages 5987–6001. PMLR, 28–30 Mar 2022.
- Going deeper with image transformers, 2021.
- Attention is all you need, 2023.
- Effective approaches to attention-based neural machine translation, 2015.
- Auto-encoding variational bayes, 2022.
- beta-VAE: Learning basic visual concepts with a constrained variational framework. In International Conference on Learning Representations, 2017.
- A point set generation network for 3d object reconstruction from a single image, 2016.
- Particle transformer for jet tagging, 2022.
- Identifying boosted objects with n-subjettiness. Journal of High Energy Physics, 2011(3), mar 2011.
- Ryan Liu (21 papers)
- Abhijith Gandrakota (9 papers)
- Jennifer Ngadiuba (28 papers)
- Maria Spiropulu (58 papers)
- Jean-Roch Vlimant (47 papers)