Abstract
Simulation is one of the key components in high energy physics. Historically it relies on the Monte Carlo methods which require a tremendous amount of computation resources. These methods may have difficulties with the expected High Luminosity Large Hadron Collider (HL-LHC) needs, so the experiments are in urgent need of new fast simulation techniques. We introduce a new Deep Learning framework based on Generative Adversarial Networks which can be faster than traditional simulation methods by 5 orders of magnitude with reasonable simulation accuracy. This approach will allow physicists to produce a sufficient amount of simulated data needed by the next HL-LHC experiments using limited computing resources.
Highlights
Simulation plays an important role in particle and nuclear physics
Such methods do not scale to meet the growing demands resulting from large quantities of data expected during High Luminosity Large Hadron Collider (HL-LHC) runs
Using the Wasserstein distance instead of the JensenShannon divergence in the Generative Adversarial Networks (GANs) objective leads to the Wasserstein GAN (WGAN) objective: min max f ∈F
Summary
Simulation plays an important role in particle and nuclear physics. It is widely used in detector design and in comparisons between experimental data and theoretical models. Simulation relies on Monte Carlo methods and requires significant computational resources. Such methods do not scale to meet the growing demands resulting from large quantities of data expected during High Luminosity Large Hadron Collider (HL-LHC) runs. A line of simulation methods that exploit the idea of reusing previously calculated or measured physical quantities have been developed to reduce the computation time [3, 4] These approaches suffer from being specific to an individual experiment and, despite being faster than the full simulation, they are not fast enough or lack accuracy. Our method for high-fidelity fast simulation of particle showers in the specific LHCb calorimeter aims to replace the existing Monte Carlo based methods and achieve a significant speed-up factor
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
