Dissipation-driven quantum generative adversarial networks

TL;DR

This paper introduces a dissipation-driven quantum GAN architecture that leverages quantum dissipation and qubit interactions to generate classical data, demonstrating preliminary feasibility through numerical tests.

Contribution

It presents a novel quantum GAN model utilizing dissipation and qubit interactions, tailored for classical data generation, with a unique training process resembling classical GANs.

Findings

Feasibility demonstrated through preliminary numerical tests.

Dissipation enables effective encoding and measurement of generated data.

The model's training process parallels classical GAN training methods.

Abstract

Quantum machine learning holds the promise of harnessing quantum advantage to achieve speedup beyond classical algorithms. Concurrently, research indicates that dissipation can serve as an effective resource in quantum computation. In this paper, we introduce a novel dissipation-driven quantum generative adversarial network (DQGAN) architecture specifically tailored for generating classical data. Our DQGAN comprises two interacting networks: a generative network and a discriminative network, both constructed from qubits. The classical data is encoded into the input qubits of the input layer via strong tailored dissipation processes. This encoding scheme enables us to extract both the generated data and the classification results by measuring the observables of the steady state of the output qubits. The network coupling weight, i.e., the strength of the interaction Hamiltonian between layers, is iteratively updated during the training process. This training procedure closely resembles the training of conventional generative adversarial networks (GANs). By alternately updating the two networks, we foster adversarial learning until the equilibrium point is reached. Our preliminary numerical test on a simplified instance of the task substantiate the feasibility of our DQGAN model.