Differentiable Learning of Quantum Circuit Born Machine

Abstract

Quantum circuit Born machines are generative models which represent the probability distribution of classical dataset as quantum pure states. Computational complexity considerations of the quantum sampling problem suggest that the quantum circuits exhibit stronger expressibility compared to classical neural networks. One can efficiently draw samples from the quantum circuits via projective measurements on qubits. However, similar to the leading implicit generative models in deep learning, such as the generative adversarial networks, the quantum circuits cannot provide the likelihood of the generated samples, which poses a challenge to the training. We devise an efficient gradient-based learning algorithm for the quantum circuit Born machine by minimizing the kerneled maximum mean discrepancy loss. We simulated generative modeling of the Bars-and-Stripes dataset and Gaussian mixture distributions using deep quantum circuits. Our experiments show the importance of circuit depth and gradient-based optimization algorithm. The proposed learning algorithm is runnable on near-term quantum device and can exhibit quantum advantages for generative modeling.

arXiv comment9 pages, 7 figures, Github page for code https://github.com/GiggleLiu/QuantumCircuitBornMachine

References in corpus (34)

• Quantum Computing in the NISQ era and beyond
• Quantum Machine Learning
• A variational eigenvalue solver on a quantum processor
• WaveNet: A Generative Model for Raw Audio
• Automatic chemical design using a data-driven continuous representation of molecules
• Hardware-efficient Variational Quantum Eigensolver for Small Molecules and Quantum Magnets
• Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks
• Quantum Circuit Learning
• Kernel methods in machine learning
• Pixel Recurrent Neural Networks
• NIPS 2016 Tutorial: Generative Adversarial Networks
• Characterizing Quantum Supremacy in Near-Term Devices
• Scalable Quantum Simulation of Molecular Energies
• Fidelity, dynamic structure factor, and susceptibility in critical phenomena
• ProjectQ: An Open Source Software Framework for Quantum Computing
• MMD GAN: Towards Deeper Understanding of Moment Matching Network
• Generative Moment Matching Networks
• Quantum Boltzmann Machine
• Hybrid Quantum-Classical Approach to Quantum Optimal Control
• Unsupervised Generative Modeling Using Matrix Product States
• Unsupervised Machine Learning on a Hybrid Quantum Computer
• Quantum Sampling Problems, BosonSampling and Quantum Supremacy
• Complexity limitations on quantum computation
• A Software Methodology for Compiling Quantum Programs
• Tomography and Generative Data Modeling via Quantum Boltzmann Training
• Quantum Variational Autoencoder
• Quantum-Assisted Learning of Hardware-Embedded Probabilistic Graphical Models
• Quantum Inference on Bayesian Networks
• Information Perspective to Probabilistic Modeling: Boltzmann Machines versus Born Machines
• Quantum Algorithms for Fixed Qubit Architectures
• Tunable Efficient Unitary Neural Networks (EUNN) and their application to RNNs
• Fidelity susceptibility made simple: A unified quantum Monte Carlo approach
• Gradient Estimators for Implicit Models
• An efficient quantum algorithm for generative machine learning

Cited by in corpus (130)

• Variational Quantum Algorithms
• Noisy intermediate-scale quantum (NISQ) algorithms
• Parameterized quantum circuits as machine learning models
• Evaluating analytic gradients on quantum hardware
• The effect of data encoding on the expressive power of variational quantum machine learning models
• A rigorous and robust quantum speed-up in supervised machine learning
• A generative modeling approach for benchmarking and training shallow quantum circuits
• Layerwise learning for quantum neural networks
• Robust data encodings for quantum classifiers
• The Expressive Power of Parameterized Quantum Circuits
• General parameter-shift rules for quantum gradients
• Experimental Quantum Generative Adversarial Networks for Image Generation
• PennyLane: Automatic differentiation of hybrid quantum-classical computations
• Barren Plateaus in Variational Quantum Computing
• Training of Quantum Circuits on a Hybrid Quantum Computer
• Is quantum advantage the right goal for quantum machine learning?
• Quantum machine learning beyond kernel methods
• Quantum agents in the Gym: a variational quantum algorithm for deep Q-learning
• Solving nonlinear differential equations with differentiable quantum circuits
• Supervised quantum machine learning models are kernel methods
• Quantum generative adversarial network for generating discrete distribution
• Generalization in Quantum Machine Learning: a Quantum Information Perspective
• The Born Supremacy: Quantum Advantage and Training of an Ising Born Machine
• Variational Quantum Eigensolver with Fewer Qubits
• Machine Learning for Quantum Matter
• Quantum Adversarial Machine Learning
• Prospects for Quantum Enhancement with Diabatic Quantum Annealing
• Yao.jl: Extensible, Efficient Framework for Quantum Algorithm Design
• Tree Tensor Networks for Generative Modeling
• Low-depth gradient measurements can improve convergence in variational hybrid quantum-classical algorithms
• Quantum Machine Learning in High Energy Physics
• Approximate amplitude encoding in shallow parameterized quantum circuits and its application to financial market indicator
• Early Fault-Tolerant Quantum Computing
• Quantum Machine Learning: from physics to software engineering
• Recent advances for quantum classifiers
• Learning and Inference on Generative Adversarial Quantum Circuits
• Neural Predictor based Quantum Architecture Search
• On the Quantum versus Classical Learnability of Discrete Distributions
• Adversarial quantum circuit learning for pure state approximation
• Analyzing the barren plateau phenomenon in training quantum neural networks with the ZX-calculus
• Learning quantum data with the quantum Earth Mover's distance
• Shadows of quantum machine learning
• Information Scrambling in Quantum Neural Networks
• Variational Quantum-Neural Hybrid Eigensolver
• Supervised Learning with Projected Entangled Pair States
• Generative model benchmarks for superconducting qubits
• Generative quantum machine learning via denoising diffusion probabilistic models
• Experimental quantum kernel machine learning with nuclear spins in a solid
• Quantum enhancements for deep reinforcement learning in large spaces
• Markovian Quantum Neuroevolution for Machine Learning
• Generalized quantum circuit differentiation rules
• Variational inference with a quantum computer
• Quantum Kernel Methods for Solving Differential Equations
• Generative Tensor Network Classification Model for Supervised Machine Learning
• Generative Quantum Learning of Joint Probability Distribution Functions
• Variational Quantum Algorithms for Dimensionality Reduction and Classification
• Expressivity of Quantum Neural Networks
• Trainability barriers and opportunities in quantum generative modeling
• Quantum Architecture Search with Meta-learning
• High Dimensional Quantum Machine Learning With Small Quantum Computers
• Scrambling Ability of Quantum Neural Networks Architectures
• Grover search revisited; application to image pattern matching
• Non-IID Quantum Federated Learning with One-shot Communication Complexity
• Universal Adversarial Examples and Perturbations for Quantum Classifiers
• Quantum semi-supervised generative adversarial network for enhanced data classification
• Probabilistic Modeling with Matrix Product States
• A single $T$-gate makes distribution learning hard
• A performance characterization of quantum generative models
• Entanglement-guided architectures of machine learning by quantum tensor network
• Automatically Differentiable Quantum Circuit for Many-qubit State Preparation
• Evolutionary Quantum Architecture Search for Parametrized Quantum Circuits
• A hybrid quantum-classical conditional generative adversarial network algorithm for human-centered paradigm in cloud
• Unsupervised Quantum Circuit Learning in High Energy Physics
• Approximate complex amplitude encoding algorithm and its application to data classification problems
• A super-polynomial quantum-classical separation for density modelling
• Quantum Quantile Mechanics: Solving Stochastic Differential Equations for Generating Time-Series
• FLIP: A flexible initializer for arbitrarily-sized parametrized quantum circuits
• Conditional Born machine for Monte Carlo event generation
• What can we learn from quantum convolutional neural networks?
• Randomness-enhanced expressivity of quantum neural networks
• Introducing Non-Linear Activations into Quantum Generative Models
• Differentiable Programming of Isometric Tensor Networks
• Hyperparameter Importance of Quantum Neural Networks Across Small Datasets
• Single-component gradient rules for variational quantum algorithms
• QDNN: DNN with Quantum Neural Network Layers
• A Continuous Variable Born Machine
• Deep learning Local Reduced Density Matrices for Many-body Hamiltonian Estimation
• On the Principles of Differentiable Quantum Programming Languages
• Protocols for classically training quantum generative models on probability distributions
• Parameterized quantum circuits as universal generative models for continuous multivariate distributions
• QTN-VQC: An End-to-End Learning framework for Quantum Neural Networks
• Bayesian Learning of Parameterised Quantum Circuits
• Resource frugal optimizer for quantum machine learning
• NISQ-compatible approximate quantum algorithm for unconstrained and constrained discrete optimization
• Splitting and Parallelizing of Quantum Convolutional Neural Networks for Learning Translationally Symmetric Data
• A Photonic Parameter-shift Rule: Enabling Gradient Computation for Photonic Quantum Computers
• F-Divergences and Cost Function Locality in Generative Modelling with Quantum Circuits
• Protocols for Trainable and Differentiable Quantum Generative Modelling
• Benchmarking Quantum Generative Learning: A Study on Scalability and Noise Resilience using QUARK
• Quantum self-learning Monte Carlo with quantum Fourier transform sampler
• Quantum Kernel Evaluation via Hong-Ou-Mandel Interference
• Variational measurement-based quantum computation for generative modeling
• Quantum neural compressive sensing for ghost imaging
• Optimisation-free Classification and Density Estimation with Quantum Circuits
• Precise Image Generation on Current Noisy Quantum Computing Devices
• QSlack: A slack-variable approach for variational quantum semi-definite programming
• Error-mitigated photonic quantum circuit Born machine
• Trade-off between Gradient Measurement Efficiency and Expressivity in Deep Quantum Neural Networks
• Tensor tree learns hidden relational structures in data to construct generative models
• Experimental benchmarking of quantum state overlap estimation strategies with photonic systems
• Bayesian Quantum Circuit
• Noise tailoring for Robust Amplitude Estimation
• Multidimensional Quantum Generative Modeling by Quantum Hartley Transform
• VQE-generated quantum circuit dataset for machine learning
• Variational post-selection for ground states and thermal states simulation
• Variational Inference for Quantum HyperNetworks
• Adaptive Circuit Learning of Born Machine: Towards Realization of Amplitude Embedding and Quantum Data Loading
• Quantum circuit-like learning: A fast and scalable classical machine-learning algorithm with similar performance to quantum circuit learning
• Detecting Entanglement Generating Circuits in Cloud-Based Quantum Computing
• Quantum generative modeling for financial time series with temporal correlations
• Modeling stochastic eye tracking data: A comparison of quantum generative adversarial networks and Markov models
• Subtractive Mixture Models via Squaring: Representation and Learning
• On the learning abilities of photonic continuous-variable Born machines
• The Dual Role of Low-Weight Pauli Propagation: A Flawed Simulator but a Powerful Initializer for Variational Quantum Algorithms
• Superior resilience to poisoning and amenability to unlearning in quantum machine learning
• Classical Neural Networks on Quantum Devices via Tensor Network Disentanglers: A Case Study in Image Classification
• Quantum Chebyshev Probabilistic Models for Fragmentation Functions
• Variational Quantum Generative Modeling by Sampling Expectation Values of Tunable Observables
• Quantum Compressive Sensing: Mathematical Machinery, Quantum Algorithms, and Quantum Circuitry
• Mode connectivity in the QCBM loss landscape