Recent advances for quantum neural networks in generative learning
Quantum computers are next-generation devices that hold promise to perform calculations beyond the reach of classical computers. A leading method towards achieving this goal is through quantum machine learning, especially quantum generative learning. Due to the intrinsic probabilistic nature of quan...
| Main Authors: | , , , , , , , , , , , , , |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2023
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/172182 |
| _version_ | 1826112569984679936 |
|---|---|
| author | Tian, Jinkai Sun, Xiaoyu Du, Yuxuan Zhao, Shanshan Liu, Qing Zhang, Kaining Yi, Wei Huang, Wanrong Wang, Chaoyue Wu, Xingyao Hsieh, Min-Hsiu Liu, Tongliang Yang, Wenjing Tao, Dacheng |
| author2 | School of Physical and Mathematical Sciences |
| author_facet | School of Physical and Mathematical Sciences Tian, Jinkai Sun, Xiaoyu Du, Yuxuan Zhao, Shanshan Liu, Qing Zhang, Kaining Yi, Wei Huang, Wanrong Wang, Chaoyue Wu, Xingyao Hsieh, Min-Hsiu Liu, Tongliang Yang, Wenjing Tao, Dacheng |
| author_sort | Tian, Jinkai |
| collection | NTU |
| description | Quantum computers are next-generation devices that hold promise to perform calculations beyond the reach of classical computers. A leading method towards achieving this goal is through quantum machine learning, especially quantum generative learning. Due to the intrinsic probabilistic nature of quantum mechanics, it is reasonable to postulate that quantum generative learning models (QGLMs) may surpass their classical counterparts. As such, QGLMs are receiving growing attention from the quantum physics and computer science communities, where various QGLMs that can be efficiently implemented on near-term quantum machines with potential computational advantages are proposed. In this paper, we review the current progress of QGLMs from the perspective of machine learning. Particularly, we interpret these QGLMs, covering quantum circuit Born machines, quantum generative adversarial networks, quantum Boltzmann machines, and quantum variational autoencoders, as the quantum extension of classical generative learning models. In this context, we explore their intrinsic relations and their fundamental differences. We further summarize the potential applications of QGLMs in both conventional machine learning tasks and quantum physics. Last, we discuss the challenges and further research directions for QGLMs. |
| first_indexed | 2024-10-01T03:09:14Z |
| format | Journal Article |
| id | ntu-10356/172182 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T03:09:14Z |
| publishDate | 2023 |
| record_format | dspace |
| spelling | ntu-10356/1721822023-11-28T06:29:56Z Recent advances for quantum neural networks in generative learning Tian, Jinkai Sun, Xiaoyu Du, Yuxuan Zhao, Shanshan Liu, Qing Zhang, Kaining Yi, Wei Huang, Wanrong Wang, Chaoyue Wu, Xingyao Hsieh, Min-Hsiu Liu, Tongliang Yang, Wenjing Tao, Dacheng School of Physical and Mathematical Sciences Science::Physics Generative Learning Quantum Generative Learning Quantum computers are next-generation devices that hold promise to perform calculations beyond the reach of classical computers. A leading method towards achieving this goal is through quantum machine learning, especially quantum generative learning. Due to the intrinsic probabilistic nature of quantum mechanics, it is reasonable to postulate that quantum generative learning models (QGLMs) may surpass their classical counterparts. As such, QGLMs are receiving growing attention from the quantum physics and computer science communities, where various QGLMs that can be efficiently implemented on near-term quantum machines with potential computational advantages are proposed. In this paper, we review the current progress of QGLMs from the perspective of machine learning. Particularly, we interpret these QGLMs, covering quantum circuit Born machines, quantum generative adversarial networks, quantum Boltzmann machines, and quantum variational autoencoders, as the quantum extension of classical generative learning models. In this context, we explore their intrinsic relations and their fundamental differences. We further summarize the potential applications of QGLMs in both conventional machine learning tasks and quantum physics. Last, we discuss the challenges and further research directions for QGLMs. This work was supported in part by the National Natural Science Foundation of China under Grants 91948303-1, 61803375, 12002380, 62106278, 62101575, and 61906210, in part by the National Key R&D Program of China under Grant 2021ZD0140301, and in part by the National University of Defense Technology Foundation under Grant ZK20-52. 2023-11-28T06:29:56Z 2023-11-28T06:29:56Z 2023 Journal Article Tian, J., Sun, X., Du, Y., Zhao, S., Liu, Q., Zhang, K., Yi, W., Huang, W., Wang, C., Wu, X., Hsieh, M., Liu, T., Yang, W. & Tao, D. (2023). Recent advances for quantum neural networks in generative learning. IEEE Transactions On Pattern Analysis and Machine Intelligence, 45(10), 12321-12340. https://dx.doi.org/10.1109/TPAMI.2023.3272029 0162-8828 https://hdl.handle.net/10356/172182 10.1109/TPAMI.2023.3272029 37126624 2-s2.0-85159800959 10 45 12321 12340 en IEEE Transactions on Pattern Analysis and Machine Intelligence © 2023 IEEE. All rights reserved. |
| spellingShingle | Science::Physics Generative Learning Quantum Generative Learning Tian, Jinkai Sun, Xiaoyu Du, Yuxuan Zhao, Shanshan Liu, Qing Zhang, Kaining Yi, Wei Huang, Wanrong Wang, Chaoyue Wu, Xingyao Hsieh, Min-Hsiu Liu, Tongliang Yang, Wenjing Tao, Dacheng Recent advances for quantum neural networks in generative learning |
| title | Recent advances for quantum neural networks in generative learning |
| title_full | Recent advances for quantum neural networks in generative learning |
| title_fullStr | Recent advances for quantum neural networks in generative learning |
| title_full_unstemmed | Recent advances for quantum neural networks in generative learning |
| title_short | Recent advances for quantum neural networks in generative learning |
| title_sort | recent advances for quantum neural networks in generative learning |
| topic | Science::Physics Generative Learning Quantum Generative Learning |
| url | https://hdl.handle.net/10356/172182 |
| work_keys_str_mv | AT tianjinkai recentadvancesforquantumneuralnetworksingenerativelearning AT sunxiaoyu recentadvancesforquantumneuralnetworksingenerativelearning AT duyuxuan recentadvancesforquantumneuralnetworksingenerativelearning AT zhaoshanshan recentadvancesforquantumneuralnetworksingenerativelearning AT liuqing recentadvancesforquantumneuralnetworksingenerativelearning AT zhangkaining recentadvancesforquantumneuralnetworksingenerativelearning AT yiwei recentadvancesforquantumneuralnetworksingenerativelearning AT huangwanrong recentadvancesforquantumneuralnetworksingenerativelearning AT wangchaoyue recentadvancesforquantumneuralnetworksingenerativelearning AT wuxingyao recentadvancesforquantumneuralnetworksingenerativelearning AT hsiehminhsiu recentadvancesforquantumneuralnetworksingenerativelearning AT liutongliang recentadvancesforquantumneuralnetworksingenerativelearning AT yangwenjing recentadvancesforquantumneuralnetworksingenerativelearning AT taodacheng recentadvancesforquantumneuralnetworksingenerativelearning |