Quantum Generative Adversarial Learning
Generative adversarial networks represent a powerful tool for classical machine learning: a generator tries to create statistics for data that mimics those of a true data set, while a discriminator tries to discriminate between the true and fake data. The learning process for generator and discrimin...
| Main Authors: | , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | English |
| Published: |
American Physical Society
2018
|
| Online Access: | http://hdl.handle.net/1721.1/117204 |
| _version_ | 1826203954947555328 |
|---|---|
| author | Lloyd, Seth Weedbrook, Christian |
| author2 | Massachusetts Institute of Technology. Department of Mechanical Engineering |
| author_facet | Massachusetts Institute of Technology. Department of Mechanical Engineering Lloyd, Seth Weedbrook, Christian |
| author_sort | Lloyd, Seth |
| collection | MIT |
| description | Generative adversarial networks represent a powerful tool for classical machine learning: a generator tries to create statistics for data that mimics those of a true data set, while a discriminator tries to discriminate between the true and fake data. The learning process for generator and discriminator can be thought of as an adversarial game, and under reasonable assumptions, the game converges to the point where the generator generates the same statistics as the true data and the discriminator is unable to discriminate between the true and the generated data. This Letter introduces the notion of quantum generative adversarial networks, where the data consist either of quantum states or of classical data, and the generator and discriminator are equipped with quantum information processors. We show that the unique fixed point of the quantum adversarial game also occurs when the generator produces the same statistics as the data. Neither the generator nor the discriminator perform quantum tomography; linear programing drives them to the optimal. Since quantum systems are intrinsically probabilistic, the proof of the quantum case is different from—and simpler than—the classical case. We show that, when the data consist of samples of measurements made on high-dimensional spaces, quantum adversarial networks may exhibit an exponential advantage over classical adversarial networks. |
| first_indexed | 2024-09-23T12:46:04Z |
| format | Article |
| id | mit-1721.1/117204 |
| institution | Massachusetts Institute of Technology |
| language | English |
| last_indexed | 2024-09-23T12:46:04Z |
| publishDate | 2018 |
| publisher | American Physical Society |
| record_format | dspace |
| spelling | mit-1721.1/1172042022-10-01T11:01:23Z Quantum Generative Adversarial Learning Lloyd, Seth Weedbrook, Christian Massachusetts Institute of Technology. Department of Mechanical Engineering Lloyd, Seth Weedbrook, Christian Generative adversarial networks represent a powerful tool for classical machine learning: a generator tries to create statistics for data that mimics those of a true data set, while a discriminator tries to discriminate between the true and fake data. The learning process for generator and discriminator can be thought of as an adversarial game, and under reasonable assumptions, the game converges to the point where the generator generates the same statistics as the true data and the discriminator is unable to discriminate between the true and the generated data. This Letter introduces the notion of quantum generative adversarial networks, where the data consist either of quantum states or of classical data, and the generator and discriminator are equipped with quantum information processors. We show that the unique fixed point of the quantum adversarial game also occurs when the generator produces the same statistics as the data. Neither the generator nor the discriminator perform quantum tomography; linear programing drives them to the optimal. Since quantum systems are intrinsically probabilistic, the proof of the quantum case is different from—and simpler than—the classical case. We show that, when the data consist of samples of measurements made on high-dimensional spaces, quantum adversarial networks may exhibit an exponential advantage over classical adversarial networks. 2018-07-30T18:41:54Z 2018-07-30T18:41:54Z 2018-07 2018-04 2018-07-26T18:00:13Z Article http://purl.org/eprint/type/JournalArticle 0031-9007 1079-7114 http://hdl.handle.net/1721.1/117204 Lloyd, Seth and Christian Weedbrook. "Quantum Generative Adversarial Learning." Physical Review Letters 121, 4 (July 2018): 040502 © 2018 American Physical Society en http://dx.doi.org/10.1103/PhysRevLett.121.040502 Physical Review Letters Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use. American Physical Society application/pdf American Physical Society American Physical Society |
| spellingShingle | Lloyd, Seth Weedbrook, Christian Quantum Generative Adversarial Learning |
| title | Quantum Generative Adversarial Learning |
| title_full | Quantum Generative Adversarial Learning |
| title_fullStr | Quantum Generative Adversarial Learning |
| title_full_unstemmed | Quantum Generative Adversarial Learning |
| title_short | Quantum Generative Adversarial Learning |
| title_sort | quantum generative adversarial learning |
| url | http://hdl.handle.net/1721.1/117204 |
| work_keys_str_mv | AT lloydseth quantumgenerativeadversariallearning AT weedbrookchristian quantumgenerativeadversariallearning |