Classical Neural Networks on Quantum Devices via Tensor Network Disentanglers: A Case Study in Image Classification

Abstract

We address the problem of implementing bottleneck layers from classical pre-trained neural networks on a quantum computer, with the goal of exploring intrinsically quantum ansatz for representing large linear layers within hybrid classical-quantum models. Our approach begins with a compression step in which the target linear layer is represented as an effective matrix product operator (MPO) without degrading model performance. The MPO is then further disentangled into a more compact form. This enables a hybrid classical-quantum execution scheme, where the disentangling circuits are deployed on a quantum computer while the remainder of the network -- including the disentangled MPO -- runs on classical hardware. We introduce two complementary algorithms for MPO disentangling: (i) an explicitly disentangling variational method leveraging standard tensor-network optimization techniques, and (ii) an implicitly disentangling gradient-descent-based approach. We validate these methods through a proof-of-concept translation of simple classical neural networks for MNIST and CIFAR-10 image classification into a hybrid classical-quantum form.

10 pages, 6 figures, 6 tables. Published in Physical Review Research 8, 023030 (2026). DOI: 10.1103/fmps-tjwy

References in corpus (21)

• Quantum Computing in the NISQ era and beyond
• A variational eigenvalue solver on a quantum processor
• Quantum algorithm for solving linear systems of equations
• Variational Quantum Algorithms
• Supervised learning with quantum enhanced feature spaces
• Barren plateaus in quantum neural network training landscapes
• Quantum principal component analysis
• Entanglement renormalization
• The Variational Quantum Eigensolver: a review of methods and best practices
• Expressibility and entangling capability of parameterized quantum circuits for hybrid quantum-classical algorithms
• Connecting ansatz expressibility to gradient magnitudes and barren plateaus
• A Review on Quantum Approximate Optimization Algorithm and its Variants
• Quantum Boltzmann Machine
• Algorithms for entanglement renormalization
• Differentiable Learning of Quantum Circuit Born Machine
• Lecture Notes of Tensor Network Contractions
• Encoding of Matrix Product States into Quantum Circuits of One- and Two-Qubit Gates
• Quantum Clustering with k-Means: a Hybrid Approach
• Hyper-optimized approximate contraction of tensor networks with arbitrary geometry
• Sign problem in tensor network contraction
• Positive bias makes tensor-network contraction tractable