Supervised Learning with Quantum-Inspired Tensor Networks

Abstract

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.

11 pages, 15 figures; updated version includes corrections, links to sample codes, expanded discussion, and additional references

References in corpus (5)

• Machine learning phases of matter
• DMRG and periodic boundary conditions: a quantum information perspective
• Renormalization algorithms for Quantum-Many Body Systems in two and higher dimensions
• An exact mapping between the Variational Renormalization Group and Deep Learning
• Machine learning for many-body physics: The case of the Anderson impurity model

Cited by in corpus (41)

• Learning phase transitions by confusion
• Quantum Entanglement in Neural Network States
• Machine learning quantum phases of matter beyond the fermion sign problem
• Unsupervised Generative Modeling Using Matrix Product States
• Tensor Networks for Dimensionality Reduction and Large-Scale Optimizations. Part 2 Applications and Future Perspectives
• A Neural Decoder for Topological Codes
• Tree Tensor Networks for Generative Modeling
• Machine learning of phase transitions in the percolation and XY models
• 2022 Review of Data-Driven Plasma Science
• Riemannian optimization of isometric tensor networks
• TensorNetwork for Machine Learning
• Supervised Learning with Projected Entangled Pair States
• Robust in Practice: Adversarial Attacks on Quantum Machine Learning
• Tensor networks for quantum machine learning
• Quantum Transfer Learning for Real-World, Small, and High-Dimensional Datasets
• Deep Learning and Quantum Entanglement: Fundamental Connections with Implications to Network Design
• Cost function embedding and dataset encoding for machine learning with parameterized quantum circuits
• Tensor-based algorithms for image classification
• Variational quantum algorithm for unconstrained black box binary optimization: Application to feature selection
• Modeling Sequences with Quantum States: A Look Under the Hood
• Hybrid quantum-classical classifier based on tensor network and variational quantum circuit
• Mutual Information Scaling for Tensor Network Machine Learning
• Anomaly Detection with Tensor Networks
• Markov Chain Monte Carlo Methods in Quantum Field Theories: A Modern Primer
• Quantum Annealing for Neural Network optimization problems: a new approach via Tensor Network simulations
• Loop-Free Tensor Networks for High-Energy Physics
• Efficient MPS representations and quantum circuits from the Fourier modes of classical image data
• Differentiable Physics: A Position Piece
• Deep convolutional tensor network
• Variational Autoencoder Analysis of Ising Model Statistical Distributions and Phase Transitions
• A Multi-Scale Tensor Network Architecture for Classification and Regression
• Language Modeling with Reduced Densities
• The resource theory of tensor networks
• A Support Tensor Train Machine
• Adaptive sampling-based optimization of quantics tensor trains for noisy functions: applications to quantum simulations
• Quantum Deformed Neural Networks
• Parallelized Tensor Train Learning of Polynomial Classifiers
• Complexity for deep neural networks and other characteristics of deep feature representations
• Tensorization of neural networks for improved privacy and interpretability
• Rademacher Random Projections with Tensor Networks
• A Sampling-Based Method for Tensor Ring Decomposition