Learning quantum data with the quantum Earth Mover's distance
arXiv:2101.03037 · doi:10.1088/2058-9565/ac79c9
Abstract
Quantifying how far the output of a learning algorithm is from its target is an essential task in machine learning. However, in quantum settings, the loss landscapes of commonly used distance metrics often produce undesirable outcomes such as poor local minima and exponentially decaying gradients. To overcome these obstacles, we consider here the recently proposed quantum earth mover's (EM) or Wasserstein-1 distance as a quantum analog to the classical EM distance. We show that the quantum EM distance possesses unique properties, not found in other commonly used quantum distance metrics, that make quantum learning more stable and efficient. We propose a quantum Wasserstein generative adversarial network (qWGAN) which takes advantage of the quantum EM distance and provides an efficient means of performing learning on quantum data. We provide examples where our qWGAN is capable of learning a diverse set of quantum data with only resources polynomial in the number of qubits.
References in corpus (88)
- Adam: A Method for Stochastic Optimization
- Spectral Normalization for Generative Adversarial Networks
- Variational Quantum Algorithms
- Deep Learning with Coherent Nanophotonic Circuits
- Hardware-efficient Variational Quantum Eigensolver for Small Molecules and Quantum Magnets
- Self-Attention Generative Adversarial Networks
- Barren plateaus in quantum neural network training landscapes
- A Quantum Approximate Optimization Algorithm
- Quantum Circuit Learning
- Quantum Convolutional Neural Networks
- Predicting Many Properties of a Quantum System from Very Few Measurements
- Parameterized quantum circuits as machine learning models
- Evaluating analytic gradients on quantum hardware
- Circuit-centric quantum classifiers
- Noise-Induced Barren Plateaus in Variational Quantum Algorithms
- From the Quantum Approximate Optimization Algorithm to a Quantum Alternating Operator Ansatz
- Efficient Learning for Deep Quantum Neural Networks
- Quantum Approximate Optimization Algorithm: Performance, Mechanism, and Implementation on Near-Term Devices
- Quantum computing for finance: overview and prospects
- The quest for a Quantum Neural Network
- Wasserstein GAN
- Quantum generative adversarial learning
- Quantum generative adversarial networks
- Quantum autoencoders for efficient compression of quantum data
- Quantum Generative Adversarial Networks for Learning and Loading Random Distributions
- Quantum Natural Gradient
- Continuous-variable quantum neural networks
- An initialization strategy for addressing barren plateaus in parametrized quantum circuits
- A generative modeling approach for benchmarking and training shallow quantum circuits
- Absence of Barren Plateaus in Quantum Convolutional Neural Networks
- Quantum Approximate Optimization Algorithm for MaxCut: A Fermionic View
- Layerwise learning for quantum neural networks
- Reconstructing quantum states with generative models
- The Expressive Power of Parameterized Quantum Circuits
- Quantum Computation of Electronic Transitions using a Variational Quantum Eigensolver
- Differentiable Learning of Quantum Circuit Born Machine
- Option Pricing using Quantum Computers
- Stabilizing Training of Generative Adversarial Networks through Regularization
- Quantum Image Processing and Its Application to Edge Detection: Theory and Experiment
- Efficient estimation of Pauli observables by derandomization
- Noise Resilience of Variational Quantum Compiling
- Trainability of Dissipative Perceptron-Based Quantum Neural Networks
- Quantum generative adversarial learning in a superconducting quantum circuit
- Experimental Machine Learning of Quantum States
- The Born Supremacy: Quantum Advantage and Training of an Ising Born Machine
- Optimizing Quantum Error Correction Codes with Reinforcement Learning
- Optimal quantum learning of a unitary transformation
- Quantum Adversarial Machine Learning
- Machine-learning-assisted correction of correlated qubit errors in a topological code
- On the regularization of Wasserstein GANs
- On the Mean Field and Classical Limits of Quantum Mechanics
- Geometrical Bounds of the Irreversibility in Markovian Systems
- Are there traps in quantum control landscapes?
- Machine learning quantum states in the NISQ era
- Learning in Quantum Control: High-Dimensional Global Optimization for Noisy Quantum Dynamics
- Variational Quantum Unsampling on a Quantum Photonic Processor
- Learning and Inference on Generative Adversarial Quantum Circuits
- The Quantum Wasserstein Distance of Order 1
- Tunable Efficient Unitary Neural Networks (EUNN) and their application to RNNs
- Domain wall encoding of discrete variables for quantum annealing and QAOA
- Monge Metric on the Sphere and Geometry of Quantum States
- Reversing Unknown Quantum Transformations: Universal Quantum Circuit for Inverting General Unitary Operations
- Quantum Assisted Simulator
- Quantum SDP-Solvers: Better upper and lower bounds
- A quantum algorithm to train neural networks using low-depth circuits
- Adversarial quantum circuit learning for pure state approximation
- Quantum approximate optimization is computationally universal
- Exploring constrained quantum control landscapes
- Analyzing the barren plateau phenomenon in training quantum neural networks with the ZX-calculus
- Non-commutative calculus, optimal transport and functional inequalities in dissipative quantum systems
- Quantum optimal transport with quantum channels
- The Schrödinger Equation in the Mean-Field and Semiclassical Regime
- Quantum Wasserstein Generative Adversarial Networks
- Monge Distance between Quantum States
- Robust Quantum Control in Games: an Adversarial Learning Approach
- Abrupt Transitions in Variational Quantum Circuit Training
- Foundation of Quantum Optimal Transport and Applications
- A quantum alternating operator ansatz with hard and soft constraints for lattice protein folding
- Wave Packets and the Quadratic Monge-Kantorovich Distance in Quantum Mechanics
- Quantum Codes from Neural Networks
- Quantum semi-supervised generative adversarial network for enhanced data classification
- Learning Unitaries by Gradient Descent
- Quantum Medical Imaging Algorithms
- Fast Approximation of Rotations and Hessians matrices
- The conditional entropy power inequality for quantum additive noise channels
- Balance between quantum Markov semigroups
- The Learnability of Quantum States
- Quantum polar decomposition algorithm
Cited by in corpus (32)
- Beyond Barren Plateaus: Quantum Variational Algorithms Are Swamped With Traps
- Barren Plateaus in Variational Quantum Computing
- Hybrid Quantum-Classical Generative Adversarial Network for High Resolution Image Generation
- Generative quantum machine learning via denoising diffusion probabilistic models
- Quantum Monge-Kantorovich problem and transport distance between density matrices
- Quantum Capsule Networks
- Learning quantum many-body systems from a few copies
- Explaining Quantum Circuits with Shapley Values: Towards Explainable Quantum Machine Learning
- Quantum Quantile Mechanics: Solving Stochastic Differential Equations for Generating Time-Series
- Quantum Optimal Transport
- Monotonicity of the quantum 2-Wasserstein distance
- Improving the speed of variational quantum algorithms for quantum error correction
- Quantum Wasserstein distance based on an optimization over separable states
- Energy-dependent barren plateau in bosonic variational quantum circuits
- Generative model for learning quantum ensemble via optimal transport loss
- The Wasserstein distance of order 1 for quantum spin systems on infinite lattices
- Quantum Optimal Transport: Quantum Channels and Qubits
- Hybrid Quantum Generative Adversarial Networks for Molecular Simulation and Drug Discovery
- Order quantum Wasserstein distances from couplings
- Quantum Wasserstein distance of order 1 between channels
- Quantum Computing for Data Centric Engineering and Science
- Classical shadows meet quantum optimal mass transport
- Trained quantum neural networks are Gaussian processes
- Perturbative gadgets for gate-based quantum computing: Non-recursive constructions without subspace restrictions
- Wasserstein Complexity of Quantum Circuits
- Quantum generative modeling for financial time series with temporal correlations
- Quantitative convergence of trained quantum neural networks to a Gaussian process
- Quantum Wasserstein distance between unitary operations
- Critical Scaling of the Quantum Wasserstein Distance
- Unravelling inter-channel quantum interference in below-threshold nonsequential double ionization with statistical measures
- Mean-field limit from general mixtures of experts to quantum neural networks
- Quantum Minimal Learning Machine: A Fidelity-Based Approach to Error Mitigation