aiqbench analysis
This research proposes a novel machine learning framework using Matrix Product States (MPS) constrained by global normalization to represent valid quantum states, bridging classical tensor network methods with quantum physics simulations. The study compares standard gradient descent against an adaptation of the Density Matrix Renormalization Group (DMRG) algorithm to determine which optimization strategy yields locally optimal tensors for these architectures. By integrating DMRG techniques into machine learning workflows, this work advances the intersection of quantum many-body physics and neural network training methodologies.
Quantum Tensor Network Learning with DMRG
arXiv:2608.18901v1 Announce Type: cross Abstract: Tensor Networks are a relatively new machine learning approach. The architectures proposed initially are inspired by approaches from quantum many-body physics simulations. One common layout is the matrix product state (MPS) also known as a tensor train optimized with gradient descent techniques. We introduce a global normalization condition, so that the MPS represents a quantum state. We investigate two optimization methods that find the locally optimal tensors and compare them regarding their effectiveness. One is based on gradient descent and the other on an adaptation of DMRG.
Abstract:Tensor Networks are a relatively new machine learning approach. The architectures proposed initially are inspired by approaches from quantum many-body physics simulations. One common layout is the matrix product state (MPS) also known as a tensor train optimized with gradient descent techniques. We introduce a global normalization condition, so that the MPS represents a quantum state. We investigate two optimization methods that find the locally optimal tensors and compare them regarding their effectiveness. One is based on gradient descent and the other on an adaptation of DMRG.
Quantum Physics (quant-ph); Machine Learning (cs.LG)
arXiv:2608.18901 [quant-ph]
(or arXiv:2608.18901v1 [quant-ph] for this version)
https://doi.org/10.48550/arXiv.2608.18901 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
ESANN 2025 Proceedings pp. 537-542
https://doi.org/10.14428/esann/2025.ES2025-157 Focus to learn more DOI(s) linking to related resources
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 199 words
Related coverage
Researchers Optimise Tensor Networks Using DMRG Method
Quantum Zeitgeist · Sep 17, 2026
Who can compete with quantum computers? Lecture notes on quantum inspired tensor networks computational techniques
arXiv · Aug 19, 2026
Who can compete with quantum computers? Lecture notes on quantum inspired tensor networks computational techniques
arXiv · Jun 15, 2026
A Block Tensor Train Burer-Monteiro Framework for Low-Rank Quantum State Tomography
arXiv · Sep 10, 2026