A matrix product state model for simultaneous classification and generation

Mossi, Alex (author), Žunkovič, Bojan (author), Flouris, Kyriakos (author)

Quantum machine learning (QML) is a rapidly expanding field that merges the principles of quantum computing with the techniques of machine learning. One of the powerful mathematical frameworks in this domain is tensor networks. These networks are used to approximate high-order tensors by contracting tensors with lower ranks. Initially developed for simulating quantum systems, tensor networks have become integral to quantum computing and, by extension, to QML. Drawing inspiration from these quantum methods, specifically the Matrix Product States (MPS), we apply them in a classical machine learning setting. Their ability to efficiently represent and manipulate complex, high-dimensional data makes them effective in a supervised learning framework. Here, we present an MPS model, in which the MPS functions as both a classifier and a generator. The dual functionality of this novel MPS model permits a strategy that enhances the traditional training of supervised MPS models. This framework is inspired by generative adversarial networks and is geared towards generating more realistic samples by reducing outliers. In addition, our contributions offer insights into the mechanics of tensor network methods for generation tasks. Specifically, we discuss alternative embedding functions and a new sampling method from non-normalized MPSs.

• Language: English
• Keywords: tensor networks, MPS, GAN, noise robustness, outlier reduction, quantum embeddings
• Work type: Article
• Typology: 1.01 - Original Scientific Article
• Organization: FRI - Faculty of Computer and Information Science
• Publication status: Published
• Publication version: Version of Record
• Year: 2025
• Number of pages: 18 str.
• Numbering: Vol. 7, art.. ǂ48
• PID: 20.500.12556/RUL-171597
• UDC: 004.85
• ISSN on article: 2524-4914
• DOI: 10.1007/s42484-025-00272-6
• COBISS.SI-ID: 232768771
• Publication date in RUL: 28.08.2025

Record is a part of a journal

• Title: Quantum machine intelligence
• Shortened title: Quantum Mach. Intell.
• Publisher: Springer Nature
• ISSN: 2524-4914
• COBISS.SI-ID: 80757763

Licences

• License: CC BY 4.0, Creative Commons Attribution 4.0 International
• Link: http://creativecommons.org/licenses/by/4.0/
• Description: This is the standard Creative Commons license that gives others maximum freedom to do what they want with the work as long as they credit the author.

Secondary language

• Language: Slovenian
• Keywords: tenzorske mreže, matrično produktni nastavki, generativni modeli, robustnost na šum, kvantne vložitve, zmanjšanje večjih odstopanj

Projects

• Funder: Other - Other funder or multiple funders
• Funding programme: 2022-531

• Funder: Other - Other funder or multiple funders
• Project number: 2022-643