Zobrazeno 1 - 10
of 503
pro vyhledávání: '"Tobias, Golling"'
Publikováno v:
European Physical Journal C: Particles and Fields, Vol 84, Iss 6, Pp 1-16 (2024)
Abstract Being able to decorrelate a feature space from protected attributes is an area of active research and study in ethics, fairness, and also natural sciences. We introduce a novel decorrelation method using Convex Neural Optimal Transport Solve
Externí odkaz:
https://doaj.org/article/2a57c64ed4ab41ffacca697c9a837736
Publikováno v:
Journal of High Energy Physics, Vol 2024, Iss 4, Pp 1-32 (2024)
Abstract We introduce a new technique called Drapes to enhance the sensitivity in searches for new physics at the LHC. By training diffusion models on side-band data, we show how background templates for the signal region can be generated either dire
Externí odkaz:
https://doaj.org/article/d17cf2262d3243c7bebf05e1e8a943e2
Autor:
Tobias Golling, Gregor Kasieczka, Claudius Krause, Radha Mastandrea, Benjamin Nachman, John Andrew Raine, Debajyoti Sengupta, David Shih, Manuel Sommerhalder
Publikováno v:
European Physical Journal C: Particles and Fields, Vol 84, Iss 3, Pp 1-21 (2024)
Abstract Machine learning-based anomaly detection (AD) methods are promising tools for extending the coverage of searches for physics beyond the Standard Model (BSM). One class of AD methods that has received significant attention is resonant anomaly
Externí odkaz:
https://doaj.org/article/7bb2652dadb34dc8a8cda8fe8534fcdf
Publikováno v:
SciPost Physics, Vol 17, Iss 2, p 046 (2024)
Model independent techniques for constructing background data templates using generative models have shown great promise for use in searches for new physics processes at the LHC. We introduce \FfF, a major improvement to the CURTAINs method by traini
Externí odkaz:
https://doaj.org/article/ca79e33ca3d44c28960629c92307a6fd
Autor:
Tobias Golling, Lukas Heinrich, Michael Kagan, Samuel Klein, Matthew Leigh, Margarita Osadchy, John Andrew Raine
Publikováno v:
Machine Learning: Science and Technology, Vol 5, Iss 3, p 035074 (2024)
We propose masked particle modeling (MPM) as a self-supervised method for learning generic, transferable, and reusable representations on unordered sets of inputs for use in high energy physics (HEP) scientific data. This work provides a novel scheme
Externí odkaz:
https://doaj.org/article/83d8259a8d4442a9852c4ce61521cb09
Autor:
Matthew Leigh, Debajyoti Sengupta, Guillaume Quétant, John Andrew Raine, Knut Zoch, Tobias Golling
Publikováno v:
SciPost Physics, Vol 16, Iss 1, p 018 (2024)
In this paper, we present a new method to efficiently generate jets in High Energy Physics called PC-JeDi. This method utilises score-based diffusion models in conjunction with transformers which are well suited to the task of generating jets as part
Externí odkaz:
https://doaj.org/article/a811948a15cf456dad051c2a0234485b
CURTAINs for your sliding window: Constructing unobserved regions by transforming adjacent intervals
Publikováno v:
Frontiers in Big Data, Vol 6 (2023)
We propose a new model independent technique for constructing background data templates for use in searches for new physics processes at the LHC. This method, called Curtains, uses invertible neural networks to parameterise the distribution of side b
Externí odkaz:
https://doaj.org/article/d0dceb7cec28449b98056dad49ac8f6c
Publikováno v:
SciPost Physics, Vol 14, Iss 6, p 159 (2023)
We present $\nu$-Flows, a novel method for restricting the likelihood space of neutrino kinematics in high-energy collider experiments using conditional normalising flows and deep invertible neural networks. This method allows the recovery of the fu
Externí odkaz:
https://doaj.org/article/65c2e632c46d414da535f09e7d2b659b
Publikováno v:
Physical Review
Resonant anomaly detection is a promising framework for model-independent searches for new particles. Weakly supervised resonant anomaly detection methods compare data with a potential signal against a template of the Standard Model (SM) background i
Publikováno v:
Physical Review
We present a detailed study on Variational Autoencoders (VAEs) for anomalous jet tagging at the Large Hadron Collider. By taking in low-level jet constituents' information, and training with background QCD jets in an unsupervised manner, the VAE is a