On the challenges of using D-Wave computers to sample Boltzmann Random Variables
Quantum Physics
2021-12-02 v2 Machine Learning
Abstract
Sampling random variables following a Boltzmann distribution is an NP-hard problem involved in various applications such as training of \textit{Boltzmann machines}, a specific kind of neural network. Several attempts have been made to use a D-Wave quantum computer to sample such a distribution, as this could lead to significant speedup in these applications. Yet, at present, several challenges remain to efficiently perform such sampling. We detail the various obstacles and explain the remaining difficulties in solving the sampling problem on a D-wave machine.
Keywords
Cite
@article{arxiv.2111.15295,
title = {On the challenges of using D-Wave computers to sample Boltzmann Random Variables},
author = {Thomas Pochart and Paulin Jacquot and Joseph Mikael},
journal= {arXiv preprint arXiv:2111.15295},
year = {2021}
}