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.

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

References in corpus (7)

• The density-matrix renormalization group in the age of matrix product states
• NICE: Non-linear Independent Components Estimation
• Tensor renormalization group approach to 2D classical lattice models
• Renormalization algorithms for Quantum-Many Body Systems in two and higher dimensions
• The Ising Model for Neural Data: Model Quality and Approximate Methods for Extracting Functional Connectivity
• Entanglement entropy of critical spin liquids
• Learning Relevant Features of Data with Multi-scale Tensor Networks

Cited by in corpus (151)

• 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
• 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
• Machine Learning by Unitary Tensor Network of Hierarchical Tree Structure
• Variational Quantum Reinforcement Learning via Evolutionary Optimization
• 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
• Accurate simulation for finite projected entangled pair states in two dimensions
• Tensor networks for quantum machine learning
• Importance sampling of randomized measurements for probing entanglement
• Density Matrix Renormalization Group with Tensor Processing Units
• Direct sampling of projected entangled-pair states
• Automatic Differentiation for Second Renormalization of Tensor Networks
• From Tensor Network Quantum States to Tensorial Recurrent Neural Networks
• Tensor networks for unsupervised machine learning
• Gauging tensor networks with belief propagation
• Tree tensor network classifiers for machine learning: from quantum-inspired to quantum-assisted
• Generative machine learning with tensor networks: benchmarks on near-term quantum computers
• Probabilistic Modeling with Matrix Product States
• Deep Quantum Geometry of Matrices
• Ab-initio study of interacting fermions at finite temperature with neural canonical transformation
• Compressing deep neural networks by matrix product operators
• Entanglement-guided architectures of machine learning by quantum tensor network
• Scalable Quantum Tomography with Fidelity Estimation
• Matrix Product States for Quantum Stochastic Modelling
• Magnetization of the spin-1/2 Heisenberg antiferromagnet on the triangular lattice
• Hybrid quantum-classical classifier based on tensor network and variational quantum circuit
• 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
• 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
• Anomaly Detection with Tensor Networks
• Detecting Chiral Magnetic Effect via Deep Learning
• Tangent-Space Gradient Optimization of Tensor Network for Machine Learning
• Quantum Annealing for Neural Network optimization problems: a new approach via Tensor Network simulations
• Scalably learning quantum many-body Hamiltonians from dynamical data
• Unsupervised Recognition of Informative Features via Tensor Network Machine Learning and Quantum Entanglement Variations
• Symmetric Tensor Networks for Generative Modeling and Constrained Combinatorial Optimization
• Introducing Non-Linear Activations into Quantum Generative Models
• Differentiable Programming of Isometric Tensor Networks
• Learning Effective Spin Hamiltonian of Quantum Magnet
• Quantum-inspired event reconstruction with Tensor Networks: Matrix Product States
• Residual Tensor Train: A Quantum-inspired Approach for Learning Multiple Multilinear Correlations
• Deterministic and Entanglement-Efficient Preparation of Amplitude-Encoded Quantum Registers
• Autoregressive neural Slater-Jastrow ansatz for variational Monte Carlo simulation
• Machine learning with tree tensor networks, CP rank constraints, and tensor dropout
• 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
• Application of quantum-inspired generative models to small molecular datasets
• 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
• Measures of distinguishability between stochastic processes
• Quantum self-learning Monte Carlo with quantum Fourier transform sampler
• A Multi-Scale Tensor Network Architecture for Classification and Regression
• Stack operation of tensor networks
• Shortcut Matrix Product States and its applications
• Density Matrix Renormalization Group Algorithm For Mixed Quantum States
• Error-correction properties of an interacting topological insulator
• Tensor network to learn the wavefunction of data
• Network-Initialized Monte Carlo Based on Generative Neural Networks
• Residual Matrix Product State for Machine Learning
• Adaptive Learning of Tensor Network Structures
• Solving Quantum Statistical Mechanics with Variational Autoregressive Networks and Quantum Circuits
• Quantum-Classical Machine learning by Hybrid Tensor Networks
• 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
• QSlack: A slack-variable approach for variational quantum semi-definite programming
• Probabilistic Inference in the Era of Tensor Networks and Differential Programming
• Supervised Training of Neural-Network Quantum States for the Next Nearest Neighbor Ising model
• Tensor Networks for Probabilistic Sequence Modeling
• Tensor networks and efficient descriptions of classical data
• Exploring explicit coarse-grained structure in artificial neural networks
• 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
• Tensor tree learns hidden relational structures in data to construct generative models
• Probabilistic Graphical Models and Tensor Networks: A Hybrid Framework
• Infinitely Wide Tensor Networks as Gaussian Process
• Bayesian Tensor Network with Polynomial Complexity for Probabilistic Machine Learning
• Learning of error statistics for the detection of quantum phases
• Kibble-Zurek mechanism and errors of gapped quantum phases
• Efficient Optimization of Variational Autoregressive Networks with Natural Gradient
• Effective classical correspondence of the Mott transition
• Neural Unfolding of the Chiral Magnetic Effect in Heavy-Ion Collisions
• Quantum Tensor Networks, Stochastic Processes, and Weighted Automata
• Lower and Upper Bounds on the VC-Dimension of Tensor Network Models
• Long-range spin-orbital order in the spin-orbital SU(2)$\times$SU(2)$\times$U(1) model
• Universal scaling laws in quantum-probabilistic machine learning by tensor network towards interpreting representation and generalization powers
• A Tensor Network Approach to Finite Markov Decision Processes
• Adaptive sampling-based optimization of quantics tensor trains for noisy functions: applications to quantum simulations
• Self-consistent tensor network method for correlated super-moiré matter beyond one billion sites
• Tensor-Networks-based Learning of Probabilistic Cellular Automata Dynamics
• Adaptive Circuit Learning of Born Machine: Towards Realization of Amplitude Embedding and Quantum Data Loading
• Tensor Network for Anomaly Detection in the Latent Space of Proton Collision Events at the LHC
• Provably efficient neural network representation for image classification
• Quantum tensor network algorithms for evaluation of spectral functions on quantum computers
• Implementing Entangled States on a Quantum Computer
• Simulating Quantum Circuits with Tree Tensor Networks using Density-Matrix Renormalization Group Algorithm
• Optimal sampling of tensor networks targeting wave function's fast decaying tails
• Tensor Network for Supervised Learning at Finite Temperature
• Tensor network method for real-space topology in quasicrystal Chern mosaics
• Subtractive Mixture Models via Squaring: Representation and Learning
• The Bayesian Method of Tensor Networks
• Quantum Dimension Reduction of Hidden Markov Models
• Patch-based Medical Image Segmentation using Matrix Product State Tensor Networks
• Using matrix-product states for time-series machine learning
• Trainable Quantum Neural Network for Multiclass Image Classification with the Power of Pre-trained Tree Tensor Networks
• Explaining Anomalies with Tensor Networks
• Learning mixed quantum states in large-scale experiments
• Neural Tangent Kernel of Matrix Product States: Convergence and Applications
• Matrix Product Operator Restricted Boltzmann Machines
• Rademacher Random Projections with Tensor Networks
• Eigen component analysis: A quantum theory incorporated machine learning technique to find linearly maximum separable components
• SchrödingeRNN: Generative Modeling of Raw Audio as a Continuously Observed Quantum State
• Block-term Tensor Neural Networks