Dual-Parameterized Quantum Circuit GAN Model in High Energy Physics

Generative models, and Adversarial Networks (GAN) in particular, are being studied as possible alternatives to Monte Carlo simulations. It has been proposed that, certain circumstances, simulation using GANs can be sped-up by quantum (qGANs). We present a new design of qGAN, the dual-Parameterized Quantum Circuit (PQC) GAN, which consists classical discriminator two generators take form PQCs. The first PQC learns probability distribution over N-pixel images, while second generates normalized pixel intensities an individual image for each input. With view HEP applications, we evaluated dual-PQC architecture on task imitating calorimeter outputs, translated into pixelated images. results demonstrate that model reproduce fixed number images with reduced size well their anticipate it should allow us scale up real outputs.