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.
Physical Review Letters
- Pub Date:
- September 2016
- Quantum Physics;
- Computer Science - Artificial Intelligence;
- Computer Science - Machine Learning
- 5+15 pages. This paper builds upon and mostly supersedes arXiv:1507.08482. In addition to results provided in this previous work, here we achieve learning improvements in more general environments, and provide connections to other work in quantum machine learning. Explicit constructions of oracularized environments given in arXiv:1507.08482 are omitted in this version