Can I read Benchmarking Quantum Hardware for Training of Fully Visible Boltzmann Machines on EtoBox?

Benchmarking Quantum Hardware for Training of Fully Visible Boltzmann Machines by Korenkevych, Dmytro; Xue, Yanbo; Bian, Zhengbing; Chudak, Fabian; Macready, William G.; Rolfe, Jason; Andriyash, Evgeny is a scholarly article available to read on EtoBox.

What is Benchmarking Quantum Hardware for Training of Fully Visible Boltzmann Machines about?

Quantum annealing (QA) is a hardware-based heuristic optimization and sampling method applicable to discrete undirected graphical models. While similar to simulated annealing, QA relies on quantum, rather than thermal, effects to explore complex search spaces. For many classes of problems, QA is known to offer computational advantages over simulated annealing. Here we report on the ability of recent QA hardware to accelerate training of fully visible Boltzmann machines. We characterize the sampling distribution of QA hardware, and show that in many cases, the quantum distributions differ significantly from classical Boltzmann distributions. In spite of this difference, training (which seeks to match data and model statistics) using standard classical gradient updates is still effective. We investigate the use of QA for seeding Markov chains as an alternative to contrastive divergence (CD) and persistent contrastive divergence (PCD). Using $k=50$ Gibbs steps, we show that for problems with high-energy barriers between modes, QA-based seeds can improve upon chains with CD and PCD initializations. For these hard problems, QA gradient estimates are more accurate, and allow for faster l

Author

Korenkevych, Dmytro; Xue, Yanbo; Bian, Zhengbing; Chudak, Fabian; Macready, William G.; Rolfe, Jason; Andriyash, Evgeny

Published

2016

Language

EN