Abstract
Abstract
In this paper, we present a method of embedding physics data manifolds with metric structure into lower dimensional spaces with simpler metrics, such as Euclidean and Hyperbolic spaces. We then demonstrate that it can be a powerful step in the data analysis pipeline for many applications. Using progressively more realistic simulated collisions at the Large Hadron Collider, we show that this embedding approach learns the underlying latent structure. With the notion of volume in Euclidean spaces, we provide for the first time a viable solution to quantifying the true search capability of model agnostic search algorithms in collider physics (i.e. anomaly detection). Finally, we discuss how the ideas presented in this paper can be employed to solve many practical challenges that require the extraction of physically meaningful representations from information in complex high dimensional datasets.
Publisher
Springer Science and Business Media LLC
Subject
Nuclear and High Energy Physics
Reference74 articles.
1. P.T. Komiske, E.M. Metodiev and J. Thaler, Metric space of collider events, Phys. Rev. Lett. 123 (2019) 041801 [arXiv:1902.02346] [INSPIRE].
2. T. Cai, J. Cheng, K. Craig and N. Craig, Which metric on the space of collider events?, Phys. Rev. D 105 (2022) 076003 [arXiv:2111.03670] [INSPIRE].
3. S. Kolouri et al., Generalized sliced Wasserstein distances, arXiv:1902.00434.
4. M. Crispim Romão et al., Use of a generalized energy Mover’s distance in the search for rare phenomena at colliders, Eur. Phys. J. C 81 (2021) 192 [arXiv:2004.09360] [INSPIRE].
5. S. Tsan et al., Particle graph autoencoders and differentiable, learned energy Mover’s distance, in the proceedings of the 35th conference on neural information processing systems, (2021) [arXiv:2111.12849] [INSPIRE].
Cited by
6 articles.
订阅此论文施引文献
订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献