Training of Generative Models for Simulation of Events With High Pile-up

Student: Solovev Aleksey

Educational Programme: Applied Mathematics and Information Science (Bachelor)

Year of Graduation: 2019

Generative models are becoming a popular approach for physical process simulations. In particular, they are widely used for modelling experiments in high-energy physics. In this study, various methods for generating responses of Cherenkov detectors used in the LHCb experiment, were proposed and implemented. The emphasis is made on modern generative deep learning models. It is possible to greatly accelerate experiments at Large Hadron Collider at CERN reproducing using such models, while at the same without losing quality of physical processes descriptions. Various generative regression models, generative adversarial networks and the Variational autoencoder are implemented in the work. The quality of the solutions was tested on the data of the LHCb experiment. The WGAN-GP method did the best for the simulation.

Student Theses at HSE must be completed in accordance with the University Rules and regulations specified by each educational programme.

Summaries of all theses must be published and made freely available on the HSE website.

The full text of a thesis can be published in open access on the HSE website only if the authoring student (copyright holder) agrees, or, if the thesis was written by a team of students, if all the co-authors (copyright holders) agree. After a thesis is published on the HSE website, it obtains the status of an online publication.

Student theses are objects of copyright and their use is subject to limitations in accordance with the Russian Federation’s law on intellectual property.

In the event that a thesis is quoted or otherwise used, reference to the author’s name and the source of quotation is required.

Search all student theses