Deep generative models for fast shower simulation in ATLAS

The need for large scale and high fidelity simulated samples for the extensive physics program of the ATLAS experiment at the Large Hadron Collider motivates the development of new simulation techniques. Building on the recent success of deep learning algorithms, Variational Auto-Encoders and Generative Adversarial Networks are investigated for modeling the response of the ATLAS electromagnetic calorimeter for photons in a central calorimeter region over a range of energies. The properties of synthesized showers are compared to showers from a full detector simulation using Geant4. This feasibility study demonstrates the potential of using such algorithms for fast calorimeter simulation for the ATLAS experiment in the future and opens the possibility to complement current simulation techniques. To em- ploy generative models for physics analyses, it is required to incorporate additional particle types and regions of the calorimeter and enhance the quality of the synthesized showers.