Conditional Generative Models for Learning Stochastic Processes
This work addresses the problem of speeding up algorithms like Monte Carlo analysis for financial modeling, particularly in pricing derivatives, but it appears incremental as it builds on existing quantum and generative adversarial network concepts.
The authors tackled the problem of learning multi-modal distributions for stochastic processes by proposing a Conditional Quantum Generative Adversarial Network (C-qGAN), which uses a quantum circuit structure to achieve more efficient state preparation than current methods. They demonstrated its effectiveness in learning tasks and applied it to price Asian option derivatives, providing a foundation for further research on path-dependent options.
A framework to learn a multi-modal distribution is proposed, denoted as the Conditional Quantum Generative Adversarial Network (C-qGAN). The neural network structure is strictly within a quantum circuit and, as a consequence, is shown to represent a more efficient state preparation procedure than current methods. This methodology has the potential to speed-up algorithms, such as Monte Carlo analysis. In particular, after demonstrating the effectiveness of the network in the learning task, the technique is applied to price Asian option derivatives, providing the foundation for further research on other path-dependent options.