Generative modeling with Gaussian Boson Sampling: classically trainable Bosonic Born Machines

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Kolarovszki, Zoltán, Bakó, Bence, Oszmaniec, Michał, Oh, Changhun, Zimborás, Zoltán
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866908880138665984
author Kolarovszki, Zoltán
Bakó, Bence
Oszmaniec, Michał
Oh, Changhun
Zimborás, Zoltán
author_facet Kolarovszki, Zoltán
Bakó, Bence
Oszmaniec, Michał
Oh, Changhun
Zimborás, Zoltán
contents Quantum generative modeling has emerged as a promising application of quantum computers, aiming to model complex probability distributions beyond the reach of classical methods. In practice, however, training such models often requires costly gradient estimation performed directly on the quantum hardware. Crucially, for certain structured quantum circuits, expectation values of local observables can be efficiently evaluated on a classical computer, enabling classical training without calls to the quantum hardware in the optimization loop. In these models, sampling from the resulting circuits can still be classically hard, so inference must be performed on a quantum device, yielding a potential computational advantage. In this work, we introduce a photonic quantum generative model built on parametrized Gaussian Boson Sampling circuits. The training is based on the efficient classical evaluation of expectation values enabled by the Gaussian structure of the state, allowing scalable optimization of the model parameters through the maximum mean discrepancy loss function. We demonstrate the effectiveness of the approach through numerical experiments on photonic systems with up to 805 modes and over a million trainable parameters, highlighting its scalability and suitability for near-term photonic quantum devices.
format Preprint
id arxiv_https___arxiv_org_abs_2603_11195
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Generative modeling with Gaussian Boson Sampling: classically trainable Bosonic Born Machines
Kolarovszki, Zoltán
Bakó, Bence
Oszmaniec, Michał
Oh, Changhun
Zimborás, Zoltán
Quantum Physics
Quantum generative modeling has emerged as a promising application of quantum computers, aiming to model complex probability distributions beyond the reach of classical methods. In practice, however, training such models often requires costly gradient estimation performed directly on the quantum hardware. Crucially, for certain structured quantum circuits, expectation values of local observables can be efficiently evaluated on a classical computer, enabling classical training without calls to the quantum hardware in the optimization loop. In these models, sampling from the resulting circuits can still be classically hard, so inference must be performed on a quantum device, yielding a potential computational advantage. In this work, we introduce a photonic quantum generative model built on parametrized Gaussian Boson Sampling circuits. The training is based on the efficient classical evaluation of expectation values enabled by the Gaussian structure of the state, allowing scalable optimization of the model parameters through the maximum mean discrepancy loss function. We demonstrate the effectiveness of the approach through numerical experiments on photonic systems with up to 805 modes and over a million trainable parameters, highlighting its scalability and suitability for near-term photonic quantum devices.
title Generative modeling with Gaussian Boson Sampling: classically trainable Bosonic Born Machines
topic Quantum Physics
url https://arxiv.org/abs/2603.11195