Systematic comparison of deep belief network training using quantum annealing vs. classical techniques
arXiv:2009.00134
Abstract
In this work we revisit and expand on a 2015 study that used a D-Wave quantum annealer as a sampling engine to assist in the training of a Deep Neural Network. The original 2015 results were reproduced using more recent D-Wave hardware. We systematically compare this quantum-assisted training method to a wider range of classical techniques, including: Contrastive Divergence with a different choice of optimizer; Contrastive Divergence with an increased number of steps (CD-k); and Simulated Annealing (SA). We find that quantum-assisted training still outperforms the CD with Gibbs sampling-based techniques; however, SA is able to match the performance of quantum-assisted training trivially using a quench-like schedule with a single sweep at high temperature followed by one at the target temperature.
arXiv comment11 pages, 11 figures
References in corpus (5)
- Quantum Annealing in the Transverse Ising Model
- Estimation of effective temperatures in quantum annealers for sampling applications: A case study with possible applications in deep learning
- Application of Quantum Annealing to Training of Deep Neural Networks
- Tomography and Generative Data Modeling via Quantum Boltzmann Training
- Searching for quantum speedup in quasistatic quantum annealers