Estimation of effective temperatures in quantum annealers for sampling applications: A case study with possible applications in deep learning
Open Access
- 9 August 2016
- journal article
- research article
- Published by American Physical Society (APS) in Physical Review A
- Vol. 94 (2) , 022308
Abstract
An increase in the efficiency of sampling from Boltzmann distributions would have a significant impact on deep learning and other machine-learning applications. Recently, quantum annealers have been proposed as a potential candidate to speed up this task, but several limitations still bar these state-of-the-art technologies from being used effectively. One of the main limitations is that, while the device may indeed sample from a Boltzmann-like distribution, quantum dynamical arguments suggest it will do so with an instance-dependent effective temperature, different from its physical temperature. Unless this unknown temperature can be unveiled, it might not be possible to effectively use a quantum annealer for Boltzmann sampling. In this work, we propose a strategy to overcome this challenge with a simple effective-temperature estimation algorithm. We provide a systematic study assessing the impact of the effective temperatures in the learning of a special class of a restricted Boltzmann machine embedded on quantum hardware, which can serve as a building block for deep-learning architectures. We also provide a comparison to -step contrastive divergence (CD-) with up to 100. Although assuming a suitable fixed effective temperature also allows us to outperform one-step contrastive divergence (CD-1), only when using an instance-dependent effective temperature do we find a performance close to that of CD-100 for the case studied here.
Keywords
All Related Versions
Funding Information
- Ames Research Center (NNA14AA60C, NAS2-03144)
This publication has 37 references indexed in Scilit:
- Maximum-Entropy Inference with a Programmable AnnealerScientific Reports, 2016
- Read the fine printNature Physics, 2015
- Quantum Support Vector Machine for Big Data ClassificationPhysical Review Letters, 2014
- Quantum principal component analysisNature Physics, 2014
- Quantum adiabatic machine learningQuantum Information Processing, 2012
- Finding low-energy conformations of lattice protein models by quantum annealingScientific Reports, 2012
- Ramsey Numbers and Adiabatic Quantum ComputingPhysical Review Letters, 2012
- A Quantum Adiabatic Evolution Algorithm Applied to Random Instances of an NP-Complete ProblemScience, 2001
- Quantum annealing in the transverse Ising modelPhysical Review E, 1998
- Quantum annealing: A new method for minimizing multidimensional functionsChemical Physics Letters, 1994