F-Divergences and Cost Function Locality in Generative Modelling with Quantum Circuits

Abstract

Generative modelling is an important unsupervised task in machine learning. In this work, we study a hybrid quantum-classical approach to this task, based on the use of a quantum circuit Born machine. In particular, we consider training a quantum circuit Born machine using $f$-divergences. We first discuss the adversarial framework for generative modelling, which enables the estimation of any $f$-divergence in the near term. Based on this capability, we introduce two heuristics which demonstrably improve the training of the Born machine. The first is based on $f$-divergence switching during training. The second introduces locality to the divergence, a strategy which has proved important in similar applications in terms of mitigating barren plateaus. Finally, we discuss the long-term implications of quantum devices for computing $f$-divergences, including algorithms which provide quadratic speedups to their estimation. In particular, we generalise existing algorithms for estimating the Kullback-Leibler divergence and the total variation distance to obtain a fault-tolerant quantum algorithm for estimating another $f$-divergence, namely, the Pearson divergence.

arXiv comment20 pages, 9 figures, 4 tables

References in corpus (48)

• Supplementary information for "Quantum supremacy using a programmable superconducting processor"
• Variational Quantum Algorithms
• Supervised learning with quantum enhanced feature spaces
• Stochastic Backpropagation and Approximate Inference in Deep Generative Models
• Barren plateaus in quantum neural network training landscapes
• The theory of variational hybrid quantum-classical algorithms
• Noisy intermediate-scale quantum (NISQ) algorithms
• Quantum machine learning in feature Hilbert spaces
• Quantum Circuit Learning
• Quantum Convolutional Neural Networks
• Characterizing Quantum Supremacy in Near-Term Devices
• Parameterized quantum circuits as machine learning models
• Cost Function Dependent Barren Plateaus in Shallow Parametrized Quantum Circuits
• Connecting ansatz expressibility to gradient magnitudes and barren plateaus
• Quantum generative adversarial networks
• Quantum autoencoders for efficient compression of quantum data
• Quantum Generative Adversarial Networks for Learning and Loading Random Distributions
• t$|$ket$⟩$ : A Retargetable Compiler for NISQ Devices
• An initialization strategy for addressing barren plateaus in parametrized quantum circuits
• A generative modeling approach for benchmarking and training shallow quantum circuits
• Robust data encodings for quantum classifiers
• Hierarchical quantum classifiers
• The Expressive Power of Parameterized Quantum Circuits
• Deep Generative Stochastic Networks Trainable by Backprop
• Average-case complexity versus approximate simulation of commuting quantum computations
• Quantum Supremacy and the Complexity of Random Circuit Sampling
• Differentiable Learning of Quantum Circuit Born Machine
• Experimental Quantum Generative Adversarial Networks for Image Generation
• Effect of barren plateaus on gradient-free optimization
• Diagnosing Barren Plateaus with Tools from Quantum Optimal Control
• Training of Quantum Circuits on a Hybrid Quantum Computer
• Quantum generative adversarial learning in a superconducting quantum circuit
• Quantum generative adversarial network for generating discrete distribution
• The Born Supremacy: Quantum Advantage and Training of an Ising Born Machine
• Equivalence of quantum barren plateaus to cost concentration and narrow gorges
• Entanglement Devised Barren Plateau Mitigation
• On barren plateaus and cost function locality in variational quantum algorithms
• Information Perspective to Probabilistic Modeling: Boltzmann Machines versus Born Machines
• Experimental Realization of a Quantum Autoencoder: The Compression of Qutrits via Machine Learning
• On the Chi square and higher-order Chi distances for approximating f-divergences
• Learning and Inference on Generative Adversarial Quantum Circuits
• Generative model benchmarks for superconducting qubits
• Variational inference with a quantum computer
• Quantum algorithms for testing properties of distributions
• Experimental Implementation of a Quantum Autoencoder via Quantum Adders
• Noise robustness and experimental demonstration of a quantum generative adversarial network for continuous distributions
• A hybrid quantum-classical conditional generative adversarial network algorithm for human-centered paradigm in cloud
• Minimax Rate-Optimal Estimation of Divergences between Discrete Distributions

Cited by in corpus (7)

• Barren Plateaus in Variational Quantum Computing
• A Lie Algebraic Theory of Barren Plateaus for Deep Parameterized Quantum Circuits
• Does provable absence of barren plateaus imply classical simulability?
• Trainability barriers and opportunities in quantum generative modeling
• Tight and Efficient Gradient Bounds for Parameterized Quantum Circuits
• Protocols for Trainable and Differentiable Quantum Generative Modelling
• Evolved Quantum Boltzmann Machines