# Generative Models for Fast Calorimeter Simulation.LHCb case

## TL;DR

This paper presents a deep learning-based generative model using GANs that significantly accelerates calorimeter simulation in high energy physics, enabling large-scale data generation for HL LHC with limited resources.

## Contribution

Introduction of a GAN-based framework that achieves faster-than-traditional calorimeter simulation by five orders of magnitude with acceptable accuracy.

## Key findings

- Simulation speed increased by 5 orders of magnitude.
- Maintains reasonable accuracy for physics analyses.
- Enables large-scale data generation for HL LHC.

## 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) need, so the experiment is 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 order of magnitude with reasonable simulation accuracy. This approach will allow physicists to produce a big enough amount of simulated data needed by the next HL LHC experiments using limited computing resources.