Quantum-enhanced machine learning

By Vedran Dunjko, Jacob M. Taylor, Hans J. Briegel. Physical Review Letters, 2016

450 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence

View Paper: https://www.semanticscholar.org/paper/ad0d1149875291d9b1177bc47e53e09237beeca0

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

Machine learning for molecular and materials science (2018, background): “The physical sciences could prove a particularly rich field for quantum learning applications.(97,98) 4.”
Machine learning \& artificial intelligence in the quantum domain (2017, background): “Motivated by the pragmatic question of the potential of quantum enhancements in general learning settings, in (Dunjko et al., 2016) it was suggested that the first step should be the identification of a quantum generalization of the AE paradigm, which underlies both RL and AI.”
Quantum computing for finance: Overview and prospects (2018, unknown): “…( √ N ) Online perceptron [26] O ( √ N ) Least-squares ﬁtting [27] O (log N ) Classical Boltzmann machine [28] O ( √ N ) Quantum Boltzmann machine [29, 30] O (log N ) Quantum PCA [22] O (log N ) Quantum support vector machine [23] O (log N ) Quantum reinforcement learning [31] O ( √ N ) Table III.”
Challenges and opportunities in quantum optimization (2023, unknown): “…oracular access to the task environment have been explored: for example, where coherent access to a unitary encoding the transition function is possible 149 , or where the environment closely mimics classical reinforcement-learning settings, allows only actions as inputs and has memory 150 .”
Quantum Machine Learning for 6G Communication Networks: State-of-the-Art and Vision for the Future (2019, background): “Previous works have separately characterized ML, QC, QML, and communication networks, see e.g., [1], [28], [29], [39]–[43], and [2], [3], [22], respectively.”
Quantum optimal control in quantum technologies. Strategic report on current status, visions and goals for research in Europe (2022, background): “For example, in quantum physics [295] it has been applied with success in many-body physics [112, 116] and quantum computing [113, 202].”
Quantum technology for military applications (2021, background): “Another situation will emerge when ML/AI is applied to quantum data; for instance, from quantum sensors or imaging [55].”
Quantum machine learning (2016, unknown): “Further, in [8] the authors analyze the types of classically speciﬁed environments which allow for quantum enhancements in learning.”
Transfer learning in hybrid classical-quantum neural networks (2019, background): “The aim of this work is to investigate the potential of the transfer learning paradigm in the context of quantum machine learning [10, 15, 40].”