Dunjko Vedran, Taylor Jacob M, Briegel Hans J
Institut für Theoretische Physik, Universität Innsbruck, Technikerstraße 21a, A-6020 Innsbruck, Austria.
Joint Quantum Institute, National Institute of Standards and Technology, Gaithersburg, Maryland 20899, USA.
Phys Rev Lett. 2016 Sep 23;117(13):130501. doi: 10.1103/PhysRevLett.117.130501. Epub 2016 Sep 20.
The emerging field of quantum machine learning has the potential to substantially aid in the problems and scope of artificial intelligence. This is only enhanced by recent successes in the field of classical machine learning. In this work we propose an approach for the systematic treatment of machine learning, from the perspective of quantum information. Our approach is general and covers all three main branches of machine learning: supervised, unsupervised, and reinforcement learning. While quantum improvements in supervised and unsupervised learning have been reported, reinforcement learning has received much less attention. Within our approach, we tackle the problem of quantum enhancements in reinforcement learning as well, and propose a systematic scheme for providing improvements. As an example, we show that quadratic improvements in learning efficiency, and exponential improvements in performance over limited time periods, can be obtained for a broad class of learning problems.
新兴的量子机器学习领域有潜力极大地助力解决人工智能的问题并拓展其范围。经典机器学习领域近期的成功更是强化了这一点。在这项工作中，我们从量子信息的角度提出一种系统处理机器学习的方法。我们的方法具有通用性，涵盖机器学习的所有三个主要分支：监督学习、无监督学习和强化学习。虽然已有关于监督学习和无监督学习的量子改进的报道，但强化学习受到的关注要少得多。在我们的方法中，我们也解决了强化学习中的量子增强问题，并提出了一个提供改进的系统方案。作为一个例子，我们表明，对于一大类学习问题，可以在学习效率上实现二次改进，在有限时间段内的性能上实现指数级改进。
