Unsupervised Generative Modeling Using Matrix Product States

Abstract

Generative modeling, which learns joint probability distribution from data and generates samples according to it, is an important task in machine learning and artificial intelligence. Inspired by probabilistic interpretation of quantum physics, we propose a generative model using matrix product states, which is a tensor network originally proposed for describing (particularly one-dimensional) entangled quantum states. Our model enjoys efficient learning analogous to the density matrix renormalization group method, which allows dynamically adjusting dimensions of the tensors and offers an efficient direct sampling approach for generative tasks. We apply our method to generative modeling of several standard datasets including the Bars and Stripes, random binary patterns and the MNIST handwritten digits to illustrate the abilities, features and drawbacks of our model over popular generative models such as Hopfield model, Boltzmann machines and generative adversarial networks. Our work sheds light on many interesting directions of future exploration on the development of quantum-inspired algorithms for unsupervised machine learning, which are promisingly possible to be realized on quantum devices.

arXiv comment11 pages, 12 figures (not including the TNs) GitHub Page: https://congzlwag.github.io/UnsupGenModbyMPS/

References in corpus (27)

• Adam: A Method for Stochastic Optimization
• Auto-Encoding Variational Bayes
• The density-matrix renormalization group in the age of matrix product states
• Area laws for the entanglement entropy - a review
• Solving the Quantum Many-Body Problem with Artificial Neural Networks
• A Practical Introduction to Tensor Networks: Matrix Product States and Projected Entangled Pair States
• Pixel Recurrent Neural Networks
• NICE: Non-linear Independent Components Estimation
• Variational Inference with Normalizing Flows
• An Area Law for One Dimensional Quantum Systems
• Tensor renormalization group approach to 2D classical lattice models
• Tensorizing Neural Networks
• Renormalization algorithms for Quantum-Many Body Systems in two and higher dimensions
• Low-Rank Tensor Networks for Dimensionality Reduction and Large-Scale Optimization Problems: Perspectives and Challenges PART 1
• Studying Two Dimensional Systems With the Density Matrix Renormalization Group
• Tensor Network Renormalization
• The computational complexity of PEPS
• Second Renormalization of Tensor-Network States
• Equivalence of restricted Boltzmann machines and tensor network states
• The Ising Model for Neural Data: Model Quality and Approximate Methods for Extracting Functional Connectivity
• Perfect Sampling with Unitary Tensor Networks
• Entanglement entropy of critical spin liquids
• On the Expressive Power of Deep Learning: A Tensor Analysis
• Learning Relevant Features of Data with Multi-scale Tensor Networks
• Supervised Learning with Quantum-Inspired Tensor Networks
• Preparing projected entangled pair states on a quantum computer
• Stochastic Matrix Product States

Cited by in corpus (152)

• Machine learning and the physical sciences
• Parameterized quantum circuits as machine learning models
• A generative modeling approach for benchmarking and training shallow quantum circuits
• Towards Quantum Machine Learning with Tensor Networks
• Differentiable Learning of Quantum Circuit Born Machine
• Differentiable Programming Tensor Networks
• Quantum Computing for High-Energy Physics: State of the Art and Challenges. Summary of the QC4HEP Working Group
• Lecture Notes of Tensor Network Contractions
• The Born Supremacy: Quantum Advantage and Training of an Ising Born Machine
• Encoding of Matrix Product States into Quantum Circuits of One- and Two-Qubit Gates
• Machine Learning for Quantum Matter
• Yao.jl: Extensible, Efficient Framework for Quantum Algorithm Design
• Tree Tensor Networks for Generative Modeling
• Identifying Quantum Phase Transitions with Adversarial Neural Networks
• Quantum neuromorphic computing
• Regressive and generative neural networks for scalar field theory
• Variational Quantum Reinforcement Learning via Evolutionary Optimization
• Machine Learning by Unitary Tensor Network of Hierarchical Tree Structure
• Information Perspective to Probabilistic Modeling: Boltzmann Machines versus Born Machines
• Quantum Machine Learning: from physics to software engineering
• Many-body topological invariants from randomized measurements
• Learning and Inference on Generative Adversarial Quantum Circuits
• Enhancing Generative Models via Quantum Correlations
• An end-to-end trainable hybrid classical-quantum classifier
• Analyzing the barren plateau phenomenon in training quantum neural networks with the ZX-calculus
• GANmapper: geographical data translation
• Contracting Arbitrary Tensor Networks: General Approximate Algorithm and Applications in Graphical Models and Quantum Circuit Simulations
• Supervised Learning with Projected Entangled Pair States
• Tensor network based machine learning of non-Markovian quantum processes
• The Presence and Absence of Barren Plateaus in Tensor-network Based Machine Learning
• Tropical Tensor Network for Ground States of Spin Glasses
• Variational inference with a quantum computer
• Matrix Product Operators for Sequence to Sequence Learning
• Generative Tensor Network Classification Model for Supervised Machine Learning
• Deep learning stochastic processes with QCD phase transition
• Multi-class quantum classifiers with tensor network circuits for quantum phase recognition
• Tensor networks for quantum machine learning
• Accurate simulation for finite projected entangled pair states in two dimensions
• Importance sampling of randomized measurements for probing entanglement
• Density Matrix Renormalization Group with Tensor Processing Units
• Direct sampling of projected entangled-pair states
• Tensor networks for unsupervised machine learning
• Automatic Differentiation for Second Renormalization of Tensor Networks
• From Tensor Network Quantum States to Tensorial Recurrent Neural Networks
• Tree tensor network classifiers for machine learning: from quantum-inspired to quantum-assisted
• Gauging tensor networks with belief propagation
• Generative machine learning with tensor networks: benchmarks on near-term quantum computers
• Probabilistic Modeling with Matrix Product States
• Deep Quantum Geometry of Matrices
• Compressing deep neural networks by matrix product operators
• Ab-initio study of interacting fermions at finite temperature with neural canonical transformation
• Scalable Quantum Tomography with Fidelity Estimation
• Entanglement-guided architectures of machine learning by quantum tensor network
• Matrix Product States for Quantum Stochastic Modelling
• Magnetization of the spin-1/2 Heisenberg antiferromagnet on the triangular lattice
• Variational quantum algorithm for unconstrained black box binary optimization: Application to feature selection
• Tensor networks for interpretable and efficient quantum-inspired machine learning
• A hybrid quantum-classical conditional generative adversarial network algorithm for human-centered paradigm in cloud
• Hybrid quantum-classical classifier based on tensor network and variational quantum circuit
• Experimental realization of a quantum image classifier via tensor-network-based machine learning
• Approximate optimization, sampling and spin-glass droplets discovery with tensor networks
• Quantum algorithm for credit valuation adjustments
• Quantum Compressed Sensing with Unsupervised Tensor-Network Machine Learning
• Detecting Chiral Magnetic Effect via Deep Learning
• Anomaly Detection with Tensor Networks
• Tangent-Space Gradient Optimization of Tensor Network for Machine Learning
• Unsupervised Recognition of Informative Features via Tensor Network Machine Learning and Quantum Entanglement Variations
• Scalably learning quantum many-body Hamiltonians from dynamical data
• Quantum Annealing for Neural Network optimization problems: a new approach via Tensor Network simulations
• Symmetric Tensor Networks for Generative Modeling and Constrained Combinatorial Optimization
• Differentiable Programming of Isometric Tensor Networks
• Introducing Non-Linear Activations into Quantum Generative Models
• Learning Effective Spin Hamiltonian of Quantum Magnet
• Quantum-inspired event reconstruction with Tensor Networks: Matrix Product States
• Deterministic and Entanglement-Efficient Preparation of Amplitude-Encoded Quantum Registers
• Residual Tensor Train: A Quantum-inspired Approach for Learning Multiple Multilinear Correlations
• Machine learning with tree tensor networks, CP rank constraints, and tensor dropout
• Autoregressive neural Slater-Jastrow ansatz for variational Monte Carlo simulation
• A tensor network discriminator architecture for classification of quantum data on quantum computers
• Tensor Networks for Medical Image Classification
• Complexity of spin configurations dynamics due to unitary evolution and periodic projective measurements
• Matrix Product Belief Propagation for reweighted stochastic dynamics over graphs
• Tensor Networks for Explainable Machine Learning in Cybersecurity
• NoRA: A Tensor Network Ansatz for Volume-Law Entangled Equilibrium States of Highly Connected Hamiltonians
• Efficient calculation of three-dimensional tensor networks
• Protocols for Trainable and Differentiable Quantum Generative Modelling
• Numerically exact mimicking of quantum gas microscopy for interacting lattice fermions
• Tensor Network Computations That Capture Strict Variationality, Volume Law Behavior, and the Efficient Representation of Neural Network States
• Application of quantum-inspired generative models to small molecular datasets
• Measures of distinguishability between stochastic processes
• A Multi-Scale Tensor Network Architecture for Classification and Regression
• Quantum self-learning Monte Carlo with quantum Fourier transform sampler
• Stack operation of tensor networks
• Residual Matrix Product State for Machine Learning
• Shortcut Matrix Product States and its applications
• Network-Initialized Monte Carlo Based on Generative Neural Networks
• Density Matrix Renormalization Group Algorithm For Mixed Quantum States
• Tensor network to learn the wavefunction of data
• Solving Quantum Statistical Mechanics with Variational Autoregressive Networks and Quantum Circuits
• Error-correction properties of an interacting topological insulator
• Adaptive Learning of Tensor Network Structures
• Correlated states in super-moiré materials with a kernel polynomial quantics tensor cross interpolation algorithm
• Learning Moment Closure in Reaction-Diffusion Systems with Spatial Dynamic Boltzmann Distributions
• Supervised Training of Neural-Network Quantum States for the Next Nearest Neighbor Ising model
• QSlack: A slack-variable approach for variational quantum semi-definite programming
• Quantum-Classical Machine learning by Hybrid Tensor Networks
• Tensor Networks for Probabilistic Sequence Modeling
• Probabilistic Inference in the Era of Tensor Networks and Differential Programming
• Non-parametric Semi-Supervised Learning in Many-body Hilbert Space with Rescaled Logarithmic Fidelity
• Cons-training Tensor Networks: Embedding and Optimization Over Discrete Linear Constraints
• Exploring explicit coarse-grained structure in artificial neural networks
• Infinitely Wide Tensor Networks as Gaussian Process
• Tensor tree learns hidden relational structures in data to construct generative models
• Probabilistic Graphical Models and Tensor Networks: A Hybrid Framework
• Tensor networks and efficient descriptions of classical data
• Bayesian Tensor Network with Polynomial Complexity for Probabilistic Machine Learning
• Efficient Optimization of Variational Autoregressive Networks with Natural Gradient
• Learning of error statistics for the detection of quantum phases
• Lower and Upper Bounds on the VC-Dimension of Tensor Network Models
• Effective classical correspondence of the Mott transition
• Quantum Tensor Networks, Stochastic Processes, and Weighted Automata
• Neural Unfolding of the Chiral Magnetic Effect in Heavy-Ion Collisions
• Kibble-Zurek mechanism and errors of gapped quantum phases
• Long-range spin-orbital order in the spin-orbital SU(2)$\times$SU(2)$\times$U(1) model
• Tensor Network for Anomaly Detection in the Latent Space of Proton Collision Events at the LHC
• Provably efficient neural network representation for image classification
• A Tensor Network Approach to Finite Markov Decision Processes
• Implementing Entangled States on a Quantum Computer
• Tensor-Networks-based Learning of Probabilistic Cellular Automata Dynamics
• Adaptive sampling-based optimization of quantics tensor trains for noisy functions: applications to quantum simulations
• Universal scaling laws in quantum-probabilistic machine learning by tensor network towards interpreting representation and generalization powers
• Self-consistent tensor network method for correlated super-moiré matter beyond one billion sites
• Adaptive Circuit Learning of Born Machine: Towards Realization of Amplitude Embedding and Quantum Data Loading
• Quantum tensor network algorithms for evaluation of spectral functions on quantum computers
• Tensor Network for Supervised Learning at Finite Temperature
• The Bayesian Method of Tensor Networks
• Subtractive Mixture Models via Squaring: Representation and Learning
• Optimal sampling of tensor networks targeting wave function's fast decaying tails
• Simulating Quantum Circuits with Tree Tensor Networks using Density-Matrix Renormalization Group Algorithm
• Tensor network method for real-space topology in quasicrystal Chern mosaics
• Matrix Product Operator Restricted Boltzmann Machines
• Quantum Dimension Reduction of Hidden Markov Models
• Learning mixed quantum states in large-scale experiments
• Explaining Anomalies with Tensor Networks
• Eigen component analysis: A quantum theory incorporated machine learning technique to find linearly maximum separable components
• Trainable Quantum Neural Network for Multiclass Image Classification with the Power of Pre-trained Tree Tensor Networks
• SchrödingeRNN: Generative Modeling of Raw Audio as a Continuously Observed Quantum State
• Using matrix-product states for time-series machine learning
• Block-term Tensor Neural Networks
• Neural Tangent Kernel of Matrix Product States: Convergence and Applications
• Rademacher Random Projections with Tensor Networks
• Patch-based Medical Image Segmentation using Matrix Product State Tensor Networks