Training Quantum Boltzmann Machines with the $\beta$-Variational Quantum Eigensolver

Abstract

The quantum Boltzmann machine (QBM) is a generative machine learning model for both classical data and quantum states. Training the QBM consists of minimizing the relative entropy from the model to the target state. This requires QBM expectation values which are computationally intractable for large models in general. It is therefore important to develop heuristic training methods that work well in practice. In this work, we study a heuristic method characterized by a nested loop: the inner loop trains the $\beta$-variational quantum eigensolver ($\beta$-VQE) by Liu et al (2021 Mach. Learn.: Sci. Technol.2 025011) to approximate the QBM expectation values; the outer loop trains the QBM to minimize the relative entropy to the target. We show that low-rank representations obtained by $\beta$-VQE provide an efficient way to learn low-rank target states, such as classical data and low-temperature quantum tomography. We test the method on both classical and quantum target data with numerical simulations of up to 10 qubits. For the cases considered here, the obtained QBMs can model the target to high fidelity. We implement a trained model on a physical quantum device. The approach offers a valuable route towards variationally training QBMs on near-term quantum devices.

arXiv comment9 pages, 11 figures

References in corpus (21)

• Quantum Computing in the NISQ era and beyond
• Variational Quantum Algorithms
• Barren plateaus in quantum neural network training landscapes
• Solving the Quantum Many-Body Problem with Artificial Neural Networks
• Quantum Circuit Learning
• Parameterized quantum circuits as machine learning models
• The Variational Quantum Eigensolver: a review of methods and best practices
• Quantum Boltzmann Machine
• Minimal Universal Two-qubit Quantum Circuits
• Searching for collective behavior in a network of real neurons
• Quantum fidelity measures for mixed states
• Tomography and Generative Data Modeling via Quantum Boltzmann Training
• Variational Thermal Quantum Simulation via Thermofield Double States
• Quantum-Assisted Learning of Hardware-Embedded Probabilistic Graphical Models
• Quantum assisted Gaussian process regression
• Variational Quantum Boltzmann Machines
• Product Spectrum Ansatz and the Simplicity of Thermal States
• Quantum Hamiltonian-Based Models and the Variational Quantum Thermalizer Algorithm
• Predicting Gibbs-State Expectation Values with Pure Thermal Shadows
• Generative training of quantum Boltzmann machines with hidden units
• Thermal variational quantum simulation on a superconducting quantum processor

Cited by in corpus (3)

• On the Sample Complexity of Quantum Boltzmann Machine Learning
• Quantum Next-Generation Reservoir Computing and Its Quantum Optical Implementation
• Fröhlich versus Bose-Einstein Condensation in Pumped Bosonic Systems