Prof. Duan’s Group Discovered a Quantum Machine Learning Algorithm Based on Generative Models

Prof. Luming Duan, CC Yao Professor at Tsinghua University, and his PH. D students Xun Gao and Zhengyu Zhang (a PhD candidate at the University of Michigan), proposed a quantum machine learning algorithm based on a quantum generative model, demonstrating the great potential of quantum computers in the field of AI research. The work, entitled “A Quantum Machine Learning Algorithm based on Generative Models”, was published recently in Science Advances.

Quantum computing and artificial intelligence, combined together, may revolutionize future technologies. A significant school of thought regarding artificial intelligence is based on generative models. Prof. Duan’s group proposed a quantum machine learning algorithm based on a quantum generative model, proving that the proposed model is more powerful to represent probability distributions compared with the classical generative models with exponential improvement and has exponential speedup in learning and inference at least for some instances if a quantum computer cannot be efficiently simulated classically. The result opens a new direction for quantum machine learning and offers a remarkable example where a quantum algorithm shows exponential improvement over classical algorithms in an important application field.

The first author of this paper is Xun Gao, a Ph. D student at Tsinghua and now a postdoc. at Harvard University. The corresponding author is Prof. Luming Duan. This research was supported with funding from the Ministry of Education and Tsinghua University.

Link for the full paper: http://advances.sciencemag.org/content/4/12/eaat9004

By Shuai Sun