Quantum-Classical Machine learning by Hybrid Tensor Networks
This work addresses the problem of improving representation power and scalability in machine learning for researchers in quantum-classical computing, though it appears incremental as it builds on existing tensor network and deep learning concepts.
The authors tackled the limitations of regular tensor networks in machine learning by proposing quantum-classical hybrid tensor networks (HTN), which integrate tensor networks with classical neural networks in a deep learning framework, enabling training with standard algorithms like Back Propagation and Stochastic Gradient Descent.
Tensor networks (TN) have found a wide use in machine learning, and in particular, TN and deep learning bear striking similarities. In this work, we propose the quantum-classical hybrid tensor networks (HTN) which combine tensor networks with classical neural networks in a uniform deep learning framework to overcome the limitations of regular tensor networks in machine learning. We first analyze the limitations of regular tensor networks in the applications of machine learning involving the representation power and architecture scalability. We conclude that in fact the regular tensor networks are not competent to be the basic building blocks of deep learning. Then, we discuss the performance of HTN which overcome all the deficiency of regular tensor networks for machine learning. In this sense, we are able to train HTN in the deep learning way which is the standard combination of algorithms such as Back Propagation and Stochastic Gradient Descent. We finally provide two applicable cases to show the potential applications of HTN, including quantum states classification and quantum-classical autoencoder. These cases also demonstrate the great potentiality to design various HTN in deep learning way.