Tensor networks for interpretable and efficient quantum-inspired machine learning

Abstract

It is a critical challenge to simultaneously gain high interpretability and efficiency with the current schemes of deep machine learning (ML). Tensor network (TN), which is a well-established mathematical tool originating from quantum mechanics, has shown its unique advantages on developing efficient ``white-box'' ML schemes. Here, we give a brief review on the inspiring progresses made in TN-based ML. On one hand, interpretability of TN ML is accommodated with the solid theoretical foundation based on quantum information and many-body physics. On the other hand, high efficiency can be rendered from the powerful TN representations and the advanced computational techniques developed in quantum many-body physics. With the fast development on quantum computers, TN is expected to conceive novel schemes runnable on quantum hardware, heading towards the ``quantum artificial intelligence'' in the forthcoming future.

12 pages, 3 figures

References in corpus (31)

• Supplementary information for "Quantum supremacy using a programmable superconducting processor"
• Towards A Rigorous Science of Interpretable Machine Learning
• Matrix Product States, Projected Entangled Pair States, and variational renormalization group methods for quantum spin systems
• Matrix Product Density Operators: Simulation of finite-T and dissipative systems
• A class of quantum many-body states that can be efficiently simulated
• Matrix product states represent ground states faithfully
• Classical simulation of infinite-size quantum lattice systems in two spatial dimensions
• Tensor renormalization group approach to 2D classical lattice models
• Criticality, the area law, and the computational power of PEPS
• Entropy scaling and simulability by Matrix Product States
• Scaling of entanglement support for Matrix Product States
• An introduction to the Ginzburg-Landau theory of phase transitions and nonequilibrium patterns
• Matrix Product States for dynamical simulation of infinite chains
• Ground state fidelity from tensor network representations
• Entropy and Entanglement in Quantum Ground States
• Explicit tensor network representation for the ground states of string-net models
• Tree Tensor Networks for Generative Modeling
• Many-body localisation implies that eigenvectors are matrix-product states
• Compressing Recurrent Neural Network with Tensor Train
• Projected Entangled Pair States at Finite Temperature: Imaginary Time Evolution with Ancillas
• Connecting Entanglement in Time and Space: Improving the Folding Algorithm
• Efficient Tensor Robust PCA under Hybrid Model of Tucker and Tensor Train
• Verifying Random Quantum Circuits with Arbitrary Geometry Using Tensor Network States Algorithm
• Hybrid quantum-classical classifier based on tensor network and variational quantum circuit
• Anomaly Detection with Tensor Networks
• Bayesian Tensorized Neural Networks with Automatic Rank Selection
• Unsupervised Recognition of Informative Features via Tensor Network Machine Learning and Quantum Entanglement Variations
• Tensor-product representations for string-net condensed states
• Generalization and Overfitting in Matrix Product State Machine Learning Architectures
• Entanglement transitions from restricted Boltzmann machines
• Predicting Quantum Potentials by Deep Neural Network and Metropolis Sampling