Many-body localized hidden generative models

TL;DR

This paper introduces a novel quantum-inspired generative model called the MBL hidden Born machine, which uses many-body localized dynamics and hidden units to improve training stability and capability in learning complex data.

Contribution

The paper proposes the MBL hidden Born machine architecture that combines MBL dynamics with hidden units, enhancing trainability and stability in quantum-inspired generative modeling.

Findings

Successfully learned MNIST-like data, quantum states, and non-local parity data.

Hidden units act as an effective thermal bath, aiding training.

MBL dynamics stabilize training trajectories.

Abstract

Born machines are quantum-inspired generative models that leverage the probabilistic nature of quantum states. Here, we present a new architecture called many-body localized (MBL) hidden Born machine that utilizes both MBL dynamics and hidden units as learning resources. We show that the hidden units act as an effective thermal bath that enhances the trainability of the system, while the MBL dynamics stabilize the training trajectories. We numerically demonstrate that the MBL hidden Born machine is capable of learning a variety of tasks, including a toy version of MNIST handwritten digits, quantum data obtained from quantum many-body states, and non-local parity data. Our architecture and algorithm provide novel strategies of utilizing quantum many-body systems as learning resources, and reveal a powerful connection between disorder, interaction, and learning in quantum many-body systems.