Guardado en:
Detalles Bibliográficos
Autores principales: Bakó, Bence, Nagy, Dániel T. R., Hága, Péter, Kallus, Zsófia, Zimborás, Zoltán
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:https://arxiv.org/abs/2405.14072
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866912359269793792
author Bakó, Bence
Nagy, Dániel T. R.
Hága, Péter
Kallus, Zsófia
Zimborás, Zoltán
author_facet Bakó, Bence
Nagy, Dániel T. R.
Hága, Péter
Kallus, Zsófia
Zimborás, Zoltán
contents Leveraging the intrinsic probabilistic nature of quantum systems, generative quantum machine learning (QML) offers the potential to outperform classical learning models. Current generative QML algorithms mostly rely on general-purpose models that, while being very expressive, face several training challenges. One potential way to address these setbacks is by constructing problem-informed models that are capable of more efficient training on structured problems. In particular, probabilistic graphical models provide a flexible framework for representing structure in generative learning problems and can thus be exploited to incorporate inductive bias into QML algorithms. In this work, we propose a problem-informed quantum circuit Born machine Ansatz for learning the joint probability distribution of random variables, with independence relations efficiently represented by a Markov network (MN). We further demonstrate the applicability of the MN framework in constructing generative learning benchmarks and compare our model's performance to previous designs, showing that it outperforms problem-agnostic circuits. Based on a preliminary analysis of trainability, we narrow down the class of MNs to those exhibiting favourable trainability properties. Finally, we discuss the potential of our model to offer quantum advantage in the context of generative learning.
format Preprint
id arxiv_https___arxiv_org_abs_2405_14072
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Problem-informed Graphical Quantum Generative Learning
Bakó, Bence
Nagy, Dániel T. R.
Hága, Péter
Kallus, Zsófia
Zimborás, Zoltán
Quantum Physics
Leveraging the intrinsic probabilistic nature of quantum systems, generative quantum machine learning (QML) offers the potential to outperform classical learning models. Current generative QML algorithms mostly rely on general-purpose models that, while being very expressive, face several training challenges. One potential way to address these setbacks is by constructing problem-informed models that are capable of more efficient training on structured problems. In particular, probabilistic graphical models provide a flexible framework for representing structure in generative learning problems and can thus be exploited to incorporate inductive bias into QML algorithms. In this work, we propose a problem-informed quantum circuit Born machine Ansatz for learning the joint probability distribution of random variables, with independence relations efficiently represented by a Markov network (MN). We further demonstrate the applicability of the MN framework in constructing generative learning benchmarks and compare our model's performance to previous designs, showing that it outperforms problem-agnostic circuits. Based on a preliminary analysis of trainability, we narrow down the class of MNs to those exhibiting favourable trainability properties. Finally, we discuss the potential of our model to offer quantum advantage in the context of generative learning.
title Problem-informed Graphical Quantum Generative Learning
topic Quantum Physics
url https://arxiv.org/abs/2405.14072