IQP Born Machines under Data-dependent and Agnostic Initialization Strategies

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Lerch, Sacha, Bowles, Joseph, Puig, Ricard, Armengol, Erik, Holmes, Zoë, Thanasilp, Supanut
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866914395663106048
author Lerch, Sacha
Bowles, Joseph
Puig, Ricard
Armengol, Erik
Holmes, Zoë
Thanasilp, Supanut
author_facet Lerch, Sacha
Bowles, Joseph
Puig, Ricard
Armengol, Erik
Holmes, Zoë
Thanasilp, Supanut
contents Quantum circuit Born machines based on instantaneous quantum polynomial-time (IQP) circuits are natural candidates for quantum generative modeling, both because of their probabilistic structure and because IQP sampling is provably classically hard in certain regimes. Recent proposals focus on training IQP-QCBMs using Maximum Mean Discrepancy (MMD) losses built from low-body Pauli-$Z$ correlators, but the effect of initialization on the resulting optimization landscape remains poorly understood. In this work, we address this by first proving that the MMD loss landscape suffers from barren plateaus for random full-angle-range initializations of IQP circuits. We then establish lower bounds on the loss variance for identity and an unbiased data-agnostic initialization. We then additionally consider a data-dependent initialization that is better aligned with the target distribution and, under suitable assumptions, yields provable gradients and generally converges quicker to a good minimum (as indicated by our training of circuits with 150 qubits on genomic data). Finally, as a by-product, the developed variance lower bound framework is applicable to a general class of non-linear losses, offering a broader toolset for analyzing warm-starts in quantum machine learning.
format Preprint
id arxiv_https___arxiv_org_abs_2603_14576
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle IQP Born Machines under Data-dependent and Agnostic Initialization Strategies
Lerch, Sacha
Bowles, Joseph
Puig, Ricard
Armengol, Erik
Holmes, Zoë
Thanasilp, Supanut
Quantum Physics
Machine Learning
Quantum circuit Born machines based on instantaneous quantum polynomial-time (IQP) circuits are natural candidates for quantum generative modeling, both because of their probabilistic structure and because IQP sampling is provably classically hard in certain regimes. Recent proposals focus on training IQP-QCBMs using Maximum Mean Discrepancy (MMD) losses built from low-body Pauli-$Z$ correlators, but the effect of initialization on the resulting optimization landscape remains poorly understood. In this work, we address this by first proving that the MMD loss landscape suffers from barren plateaus for random full-angle-range initializations of IQP circuits. We then establish lower bounds on the loss variance for identity and an unbiased data-agnostic initialization. We then additionally consider a data-dependent initialization that is better aligned with the target distribution and, under suitable assumptions, yields provable gradients and generally converges quicker to a good minimum (as indicated by our training of circuits with 150 qubits on genomic data). Finally, as a by-product, the developed variance lower bound framework is applicable to a general class of non-linear losses, offering a broader toolset for analyzing warm-starts in quantum machine learning.
title IQP Born Machines under Data-dependent and Agnostic Initialization Strategies
topic Quantum Physics
Machine Learning
url https://arxiv.org/abs/2603.14576