Abstract Inspired by coarse-graining approaches used in physics, we show how similar algorithms can be adapted for data. The resulting algorithms are based on layered tree tensor networks and scale linearly with both the dimension of the input and the training set size. Computing most of the layers with an unsupervised algorithm, then optimizing just the top layer for supervised classification of the MNIST and fashion MNIST data sets gives very good results. We also discuss mixing a prior guess for supervised weights together with an unsupervised representation of the data, yielding a smaller number of features nevertheless able to give good performance.
Tensor networks are approximations of high-order tensors which are efficient to work with and have been very successful for physics and mathematics applications. We demonstrate how algorithms for optimizing tensor networks can be adapted to supervised learning tasks by using matrix product states (tensor trains) to parameterize non-linear kernel learning models. For the MNIST data set we obtain less than 1% test set classification error. We discuss an interpretation of the additional structure imparted by the tensor network to the learned model.
Tensor networks are efficient representations of high-dimensional tensors which have been very successful for physics and mathematics applications. We demonstrate how algorithms for optimizing such networks can be adapted to supervised learning tasks by using matrix product states (tensor trains) to parameterize models for classifying images. For the MNIST data set we obtain less than 1% test set classification error. We discuss how the tensor network form imparts additional structure to the learned model and suggest a possible generative interpretation.
This chapter presents tensor networks as a unifying framework for quantum-inspired machine learning and for the analysis of near-term quantum learning models. Motivated by the challenge of high dimensionality, this chapter shows how tensor networks exploit locality, low-rank structure, and controlled correlations to represent high-order data efficiently while avoiding the exponential scaling of naïve tensor representations. Fundamental concepts including tensors, tensor contraction, and graphical network representations are introduced, followed by the development of key architectures such as Matrix Product States (Tensor Trains) and the Multi-scale Entanglement Renormalization Ansatz. Their roles in controlling expressivity, entanglement, and computational cost are emphasized throughout. This chapter further demonstrates the close correspondence between tensor networks and quantum circuits, showing how shallow quantum models can be interpreted as low-bond-dimension tensor networks and how this perspective clarifies classical simulability, representational capacity, and noisy intermediate-scale quantum (NISQ)-era limitations. Hybrid quantum-tensor network architectures are presented as a practical route for combining classical compression and representation learning with targeted quantum processing. Applications in natural language processing, biological sequence learning, and image and signal processing illustrate how tensor network methods serve as both efficient classical models and structured surrogates for quantum learning systems. Hands-on Qiskit and PennyLane examples connect these ideas to executable machine learning workflows.
We propose a restricted class of tensor network state, built from number-state preserving tensors, for supervised learning tasks. This class of tensor network is argued to be a natural choice for classifiers as 1) they map classical data to classical data, and thus preserve the interpretability of data under tensor transformations, 2) they can be efficiently trained to maximize their scalar product against classical data sets, and 3) they seem to be as powerful as generic (unrestricted) tensor networks in this task. Our proposal is demonstrated using a variety of benchmark classification problems, where number-state preserving versions of commonly used networks (including MPS, TTN and MERA) are trained as effective classifiers. This work opens the path for powerful tensor network methods such as MERA, which were previously computationally intractable as classifiers, to be employed for difficult tasks such as image recognition.
Tensor networks, originally designed to address computational problems in quantum many-body physics, have recently been applied to machine learning tasks. However, compared to quantum physics, where the reasons for the success of tensor network approaches over the last 30 years is well understood, very little is yet known about why these techniques work for machine learning. The goal of this paper is to investigate entanglement properties of tensor network models in a current machine learning application, in order to uncover general principles that may guide future developments. We revisit the use of tensor networks for supervised image classification using the MNIST data set of handwritten digits, as pioneered by Stoudenmire and Schwab [Adv. in Neur. Inform. Proc. Sys. 29, 4799 (2016)]. Firstly we hypothesize about which state the tensor network might be learning during training. For that purpose, we propose a plausible candidate state
∣Σℓ⟩ (built as a superposition of product states corresponding to images in the training set) and investigate its entanglement properties. We conclude that
∣Σℓ⟩ is so robustly entangled that it cannot be approximated by the tensor network used in that work, which must therefore be representing a very different state. Secondly, we use tensor networks with a block product structure, in which entanglement is restricted within small blocks of
n×n pixels/qubits. We find that these states are extremely expressive (e.g. training accuracy of
99.97% already for
n=2), suggesting that long-range entanglement may not be essential for image classification. However, in our current implementation, optimization leads to over-fitting, resulting in test accuracies that are not competitive with other current approaches.