Training and Classification using a Restricted Boltzmann Machine on the D-Wave 2000Q
This work addresses the computational bottleneck in RBM training for machine learning practitioners, though it is incremental as it shows comparable performance rather than a breakthrough.
The authors tackled the slow training of Restricted Boltzmann Machines (RBMs) by using a quantum annealer (D-Wave 2000Q) to compute gradients, achieving similar classification accuracy to classical contrastive divergence (CD) on a 64-bit dataset while eliminating computationally expensive MCMC steps.
Restricted Boltzmann Machine (RBM) is an energy based, undirected graphical model. It is commonly used for unsupervised and supervised machine learning. Typically, RBM is trained using contrastive divergence (CD). However, training with CD is slow and does not estimate exact gradient of log-likelihood cost function. In this work, the model expectation of gradient learning for RBM has been calculated using a quantum annealer (D-Wave 2000Q), which is much faster than Markov chain Monte Carlo (MCMC) used in CD. Training and classification results are compared with CD. The classification accuracy results indicate similar performance of both methods. Image reconstruction as well as log-likelihood calculations are used to compare the performance of quantum and classical algorithms for RBM training. It is shown that the samples obtained from quantum annealer can be used to train a RBM on a 64-bit `bars and stripes' data set with classification performance similar to a RBM trained with CD. Though training based on CD showed improved learning performance, training using a quantum annealer eliminates computationally expensive MCMC steps of CD.