Generative Adversarial Networks for the fast simulation of the Time Projection Chamber responses at the MPD detector

Detailed detector simulation models are vital for the successful operation of modern high-energy physics experiments. In most cases, running detailed models requires a significant amount of computing resources. It is desired to have approaches that are less resource-intensive. In this work, we demonstrate the applicability of Generative Adversarial Networks (GAN) as a basis for such fast-simulation models for the case of the Time Projection Chamber (TPC) at the MPD detector at the NICA accelerator complex. Our prototype GAN-based model of TPC works faster than the detailed simulation in an order of magnitude without any noticeable drop in the quality of the high-level reconstruction characteristics for the generated data. Approaches with direct and indirect quality metrics optimization are compared.