Efficient training of photonic quantum generative models

TL;DR

This paper introduces an efficient training method for photon-based quantum generative models using maximum mean discrepancy, enabling practical quantum sampling tasks with insights into initialization and ansatz effects.

Contribution

It presents a novel training procedure for photonic quantum generative models leveraging classical simulation and boson sampling, advancing quantum machine learning capabilities.

Findings

Numerical results demonstrate effective training of photonic models.

Initialization strategies significantly impact training success.

Ansatz choice influences model performance.

Abstract

The topic of generative learning has gained traction within the field of quantum machine learning, in particular with the advent of train-on-classical, deploy-on-quantum methods. This approach exploits the properties of intermediate-complexity circuits whose training can be simulated classically efficiently, but that generally require quantum hardware for the corresponding sampling problem. Quantum linear optics possess similar properties, which allows us to propose an efficient training procedure for photon-native quantum generative models based on the maximum mean discrepancy, where the deployment of the model corresponds to the task of boson sampling. We provide numerical results, propose datasets, and we also explore how initialization strategies and ansatz choice affect the training.