Generative training of quantum Boltzmann machines with hidden units

Abstract

In this article we provide a method for fully quantum generative training of quantum Boltzmann machines with both visible and hidden units while using quantum relative entropy as an objective. This is significant because prior methods were not able to do so due to mathematical challenges posed by the gradient evaluation. We present two novel methods for solving this problem. The first proposal addresses it, for a class of restricted quantum Boltzmann machines with mutually commuting Hamiltonians on the hidden units, by using a variational upper bound on the quantum relative entropy. The second one uses high-order divided difference methods and linear-combinations of unitaries to approximate the exact gradient of the relative entropy for a generic quantum Boltzmann machine. Both methods are efficient under the assumption that Gibbs state preparation is efficient and that the Hamiltonian are given by a sparse row-computable matrix.

References in corpus (15)

• Quantum Machine Learning
• Barren plateaus in quantum neural network training landscapes
• Quantum machine learning in feature Hilbert spaces
• Quantum principal component analysis
• Circuit-centric quantum classifiers
• Quantum algorithms for supervised and unsupervised machine learning
• Quantum machine learning: a classical perspective
• Restricted-Boltzmann-Machine Learning for Solving Strongly Correlated Quantum Systems
• Learning Thermodynamics with Boltzmann Machines
• Tomography and Generative Data Modeling via Quantum Boltzmann Training
• A Quantum-Quantum Metropolis Algorithm
• Hamiltonian Simulation with Optimal Sample Complexity
• Adversarial quantum circuit learning for pure state approximation
• Strategies and Networks for State-Dependent Quantum Cloning
• Quantum Language Processing

Cited by in corpus (13)

• Variational Quantum Boltzmann Machines
• On the Sample Complexity of Quantum Boltzmann Machine Learning
• Near-Optimal Quantum Algorithms for Multivariate Mean Estimation
• Exploring Unsupervised Anomaly Detection with Quantum Boltzmann Machines in Fraud Detection
• Near-Term Quantum-Classical Associative Adversarial Networks
• Towards Transfer Learning for Large-Scale Image Classification Using Annealing-based Quantum Boltzmann Machines
• Training Quantum Boltzmann Machines with the $\beta$-Variational Quantum Eigensolver
• Quantum algorithms for multivariate Monte Carlo estimation
• Group theory on quantum Boltzmann machine
• Quantum Generative Training Using Rényi Divergences
• Quantum Machine Learning For Classical Data
• The Holy Grail of Quantum Artificial Intelligence: Major Challenges in Accelerating the Machine Learning Pipeline
• Nonparametric Regression Quantum Neural Networks