Protocols for classically training quantum generative models on probability distributions

TL;DR

This paper introduces protocols for classically training quantum generative models, specifically IQP circuits, enabling efficient training and sampling for industrial distributions, potentially demonstrating quantum advantage in the NISQ era.

Contribution

It develops a classical training method for IQP-based quantum generative models that are hard to sample classically, facilitating practical quantum advantage demonstrations.

Findings

Classical simulation of IQP output distributions is feasible with efficient algorithms.

End-to-end training of IQP circuits with up to 30 qubits demonstrated on a desktop.

The approach enables training on industrially relevant distributions, advancing quantum machine learning applications.

Abstract

Quantum Generative Modelling (QGM) relies on preparing quantum states and generating samples from these states as hidden - or known - probability distributions. As distributions from some classes of quantum states (circuits) are inherently hard to sample classically, QGM represents an excellent testbed for quantum supremacy experiments. Furthermore, generative tasks are increasingly relevant for industrial machine learning applications, and thus QGM is a strong candidate for demonstrating a practical quantum advantage. However, this requires that quantum circuits are trained to represent industrially relevant distributions, and the corresponding training stage has an extensive training cost for current quantum hardware in practice. In this work, we propose protocols for classical training of QGMs based on circuits of the specific type that admit an efficient gradient computation, while remaining hard to sample. In particular, we consider Instantaneous Quantum Polynomial (IQP) circuits and their extensions. Showing their classical simulability in terms of the time complexity, sparsity and anti-concentration properties, we develop a classically tractable way of simulating their output probability distributions, allowing classical training to a target probability distribution. The corresponding quantum sampling from IQPs can be performed efficiently, unlike when using classical sampling. We numerically demonstrate the end-to-end training of IQP circuits using probability distributions for up to 30 qubits on a regular desktop computer. When applied to industrially relevant distributions this combination of classical training with quantum sampling represents an avenue for reaching advantage in the NISQ era.