Efficient training of photonic quantum generative models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Gottlieb, Felix, Mezher, Rawad, Ventura, Brian, Mansfield, Shane, Salavrakos, Alexia
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918380628344832
author Gottlieb, Felix
Mezher, Rawad
Ventura, Brian
Mansfield, Shane
Salavrakos, Alexia
author_facet Gottlieb, Felix
Mezher, Rawad
Ventura, Brian
Mansfield, Shane
Salavrakos, Alexia
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2603_08793
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Efficient training of photonic quantum generative models
Gottlieb, Felix
Mezher, Rawad
Ventura, Brian
Mansfield, Shane
Salavrakos, Alexia
Quantum Physics
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.
title Efficient training of photonic quantum generative models
topic Quantum Physics
url https://arxiv.org/abs/2603.08793