Expressive equivalence of classical and quantum restricted Boltzmann machines

TL;DR

This paper introduces a semi-quantum restricted Boltzmann machine (sqRBM) that simplifies quantum generative models, making them more practical by reducing resource demands while maintaining expressiveness comparable to classical RBMs.

Contribution

The paper proposes a semi-quantum RBM with a commuting Hamiltonian in the visible space, providing closed-form expressions and demonstrating its close relationship to classical RBMs, thus improving trainability and scalability.

Findings

sqRBMs require fewer hidden units than classical RBMs for the same distribution

Closed-form expressions for probabilities and gradients are derived for sqRBMs

Numerical simulations validate the theoretical predictions with up to 100 units

Abstract

Quantum computers offer the potential for efficiently sampling from complex probability distributions, attracting increasing interest in generative modeling within quantum machine learning. This surge in interest has driven the development of numerous generative quantum models, yet their trainability and scalability remain significant challenges. A notable example is a quantum restricted Boltzmann machine (QRBM), which is based on the Gibbs state of a parameterized non-commuting Hamiltonian. While QRBMs are expressive, their non-commuting Hamiltonians make gradient evaluation computationally demanding, even on fault-tolerant quantum computers. In this work, we propose a semi-quantum restricted Boltzmann machine (sqRBM), a model designed for classical data that mitigates the challenges associated with previous QRBM proposals. The sqRBM Hamiltonian is commuting in the visible subspace while remaining non-commuting in the hidden subspace. This structure allows us to derive closed-form expressions for both output probabilities and gradients. Leveraging these analytical results, we demonstrate that sqRBMs share a close relationship with classical restricted Boltzmann machines (RBM). Our theoretical analysis predicts that, to learn a given probability distribution, an RBM requires three times as many hidden units as an sqRBM, while both models have the same total number of parameters. We validate these findings through numerical simulations involving up to 100 units. Our results suggest that sqRBMs could enable practical quantum machine learning applications in the near future by significantly reducing quantum resource requirements.