Learnability scaling of quantum states: Restricted Boltzmann machines

paper
Published

November 15, 2019

Info

In 2022 we would have named this paper “RBM scaling laws”.

This is a quantitative study characterizing the scaling behavior of Restricted Bolzmann Machines deployed in the context of quatum state reconstruction. Published as Editors’ Suggestion in PRB.

Authors

Dan Sehayek, Anna Golubeva, Michael S. Albergo, Bohdan Kulchytskyy, Giacomo Torlai, and Roger G. Melko

Abstract

Generative modeling with machine learning has provided a new perspective on the data-driven task of reconstructing quantum states from a set of qubit measurements. As increasingly large experimental quantum devices are built in laboratories, the question of how these machine learning techniques scale with the number of qubits is becoming crucial. We empirically study the scaling of restricted Boltzmann machines (RBMs) applied to reconstruct ground-state wave functions of the one-dimensional transverse-field Ising model from projective measurement data. We define a learning criterion via a threshold on the relative error in the energy estimator of the machine. With this criterion, we observe that the number of RBM weight parameters required for accurate representation of the ground state in the worst case – near criticality – scales quadratically with the number of qubits. By pruning small parameters of the trained model, we find that the number of weights can be significantly reduced while still retaining an accurate reconstruction. This provides evidence that overparametrization of the RBM is required to facilitate the learning process.