{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T01:44:14Z","timestamp":1784857454929,"version":"3.55.0"},"reference-count":38,"publisher":"Verein zur Forderung des Open Access Publizierens in den Quantenwissenschaften","license":[{"start":{"date-parts":[[2023,3,2]],"date-time":"2023-03-02T00:00:00Z","timestamp":1677715200000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62171212"],"award-info":[{"award-number":["62171212"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Guangdong Provincial Key Laboratory","award":["2019B121203002"],"award-info":[{"award-number":["2019B121203002"]}]},{"name":"Guang- dong Basic and Applied Basic Research Foundation","award":["2022A1515010340"],"award-info":[{"award-number":["2022A1515010340"]}]},{"name":"Hong Kong Research Grant Council","award":["ECS 27310822"],"award-info":[{"award-number":["ECS 27310822"]}]}],"content-domain":{"domain":["quantum-journal.org"],"crossmark-restriction":false},"short-container-title":["Quantum"],"abstract":"<jats:p>The ability to extract relevant information is critical to learning. An ingenious approach as such is the information bottleneck, an optimisation problem whose solution corresponds to a faithful and memory-efficient representation of relevant information from a large system. The advent of the age of quantum computing calls for efficient methods that work on information regarding quantum systems. Here we address this by proposing a new and general algorithm for the quantum generalisation of information bottleneck. Our algorithm excels in the speed and the definiteness of convergence compared with prior results. It also works for a much broader range of problems, including the quantum extension of deterministic information bottleneck, an important variant of the original information bottleneck problem. Notably, we discover that a quantum system can achieve strictly better performance than a classical system of the same size regarding quantum information bottleneck, providing new vision on justifying the advantage of quantum machine learning.<\/jats:p>","DOI":"10.22331\/q-2023-03-02-936","type":"journal-article","created":{"date-parts":[[2023,3,2]],"date-time":"2023-03-02T17:05:00Z","timestamp":1677776700000},"page":"936","update-policy":"https:\/\/doi.org\/10.22331\/q-crossmark-policy-page","source":"Crossref","is-referenced-by-count":12,"title":["Efficient algorithms for quantum information bottleneck"],"prefix":"10.22331","volume":"7","author":[{"given":"Masahito","family":"Hayashi","sequence":"first","affiliation":[{"name":"Shenzhen Institute for Quantum Science and Engineering, Southern University of Science and Technology, Shenzhen,518055, China"},{"name":"International Quantum Academy (SIQA), Futian District, Shenzhen 518048, China"},{"name":"Guangdong Provincial Key Laboratory of Quantum Science and Engineering, Southern University of Science and Technology, Shenzhen, 518055, China"},{"name":"Graduate School of Mathematics, Nagoya University, Nagoya, 464-8602, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuxiang","family":"Yang","sequence":"additional","affiliation":[{"name":"QICI Quantum Information and Computation Initiative, Department of Computer Science, The University of Hong Kong, Pokfulam Road, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"9598","published-online":{"date-parts":[[2023,3,2]]},"reference":[{"key":"0","doi-asserted-by":"publisher","unstructured":"S. Arimoto. An algorithm for computing the capacity of arbitrary discrete memoryless channels. IEEE Transactions on Information Theory, 18 (1): 14\u201320, 1972. 10.1109\/TIT.1972.1054753.","DOI":"10.1109\/TIT.1972.1054753"},{"key":"1","doi-asserted-by":"publisher","unstructured":"Leonardo Banchi, Jason Pereira, and Stefano Pirandola. Generalization in quantum machine learning: A quantum information standpoint. PRX Quantum, 2: 040321, Nov 2021. 10.1103\/PRXQuantum.2.040321.","DOI":"10.1103\/PRXQuantum.2.040321"},{"key":"2","doi-asserted-by":"publisher","unstructured":"Jacob Biamonte, Peter Wittek, Nicola Pancotti, Patrick Rebentrost, Nathan Wiebe, and Seth Lloyd. Quantum machine learning. Nature, 549 (7671): 195\u2013202, 2017. 10.1038\/nature23474.","DOI":"10.1038\/nature23474"},{"key":"3","doi-asserted-by":"publisher","unstructured":"R. Blahut. Computation of channel capacity and rate-distortion functions. IEEE Transactions on Information Theory, 18 (4): 460\u2013473, 1972. 10.1109\/TIT.1972.1054855.","DOI":"10.1109\/TIT.1972.1054855"},{"key":"4","doi-asserted-by":"publisher","unstructured":"Carsten Blank, Daniel K Park, June-Koo Kevin Rhee, and Francesco Petruccione. Quantum classifier with tailored quantum kernel. npj Quantum Information, 6 (1): 1\u20137, 2020. 10.1038\/s41534-020-0272-6.","DOI":"10.1038\/s41534-020-0272-6"},{"key":"5","doi-asserted-by":"publisher","unstructured":"Nilanjana Datta, Christoph Hirche, and Andreas Winter. Convexity and operational interpretation of the quantum information bottleneck function. In 2019 IEEE International Symposium on Information Theory (ISIT), pages 1157\u20131161, 2019. 10.1109\/ISIT.2019.8849518.","DOI":"10.1109\/ISIT.2019.8849518"},{"key":"6","doi-asserted-by":"publisher","unstructured":"Andr\u00e1s Gily\u00e9n, Yuan Su, Guang Hao Low, and Nathan Wiebe. Quantum singular value transformation and beyond: exponential improvements for quantum matrix arithmetics. In Proceedings of the 51st Annual ACM SIGACT Symposium on Theory of Computing, pages 193\u2013204, 2019. 10.1145\/3313276.3316366.","DOI":"10.1145\/3313276.3316366"},{"key":"7","doi-asserted-by":"publisher","unstructured":"Ziv Goldfeld and Yury Polyanskiy. The information bottleneck problem and its applications in machine learning. IEEE Journal on Selected Areas in Information Theory, 1 (1): 19\u201338, 2020. 10.1109\/JSAIT.2020.2991561.","DOI":"10.1109\/JSAIT.2020.2991561"},{"key":"8","doi-asserted-by":"publisher","unstructured":"Arne L. Grimsmo and Susanne Still. Quantum predictive filtering. Phys. Rev. A, 94: 012338, Jul 2016. 10.1103\/PhysRevA.94.012338.","DOI":"10.1103\/PhysRevA.94.012338"},{"key":"9","doi-asserted-by":"publisher","unstructured":"Aram W Harrow, Avinatan Hassidim, and Seth Lloyd. Quantum algorithm for linear systems of equations. Physical review letters, 103 (15): 150502, 2009. 10.1103\/PhysRevLett.103.150502.","DOI":"10.1103\/PhysRevLett.103.150502"},{"key":"10","doi-asserted-by":"publisher","unstructured":"Vojt\u011bch Havl\u00ed\u010dek, Antonio D C\u00f3rcoles, Kristan Temme, Aram W Harrow, Abhinav Kandala, Jerry M Chow, and Jay M Gambetta. Supervised learning with quantum-enhanced feature spaces. Nature, 567 (7747): 209\u2013212, 2019. 10.1038\/s41586-019-0980-2.","DOI":"10.1038\/s41586-019-0980-2"},{"key":"11","doi-asserted-by":"publisher","unstructured":"Masahito Hayashi and Vincent Y. F. Tan. Minimum rates of approximate sufficient statistics. IEEE Transactions on Information Theory, 64 (2): 875\u2013888, 2018. 10.1109\/TIT.2017.2775612.","DOI":"10.1109\/TIT.2017.2775612"},{"key":"12","doi-asserted-by":"publisher","unstructured":"Carl W Helstrom. Quantum detection and estimation theory. Journal of Statistical Physics, 1 (2): 231\u2013252, 1969. 10.1007\/BF01007479.","DOI":"10.1007\/BF01007479"},{"key":"13","doi-asserted-by":"publisher","unstructured":"Christoph Hirche and Andreas Winter. An alphabet-size bound for the information bottleneck function. In 2020 IEEE International Symposium on Information Theory (ISIT), pages 2383\u20132388, 2020. 10.1109\/ISIT44484.2020.9174416.","DOI":"10.1109\/ISIT44484.2020.9174416"},{"key":"14","doi-asserted-by":"publisher","unstructured":"Alexander S Holevo. Probabilistic and statistical aspects of quantum theory, volume 1. Springer Science & Business Media, 2011. 10.1007\/978-88-7642-378-9.","DOI":"10.1007\/978-88-7642-378-9"},{"key":"15","doi-asserted-by":"publisher","unstructured":"Winston H. Hsu, Lyndon S. Kennedy, and Shih-Fu Chang. Video search reranking via information bottleneck principle. MM &apos;06, pages 35\u201344, New York, NY, USA, 2006. Association for Computing Machinery. ISBN 1595934472. 10.1145\/1180639.1180654.","DOI":"10.1145\/1180639.1180654"},{"key":"16","doi-asserted-by":"publisher","unstructured":"Seth Lloyd, Maria Schuld, Aroosa Ijaz, Josh Izaac, and Nathan Killoran. Quantum embeddings for machine learning. arXiv preprint arXiv:2001.03622, 2020. 10.48550\/arXiv.2001.03622.","DOI":"10.48550\/arXiv.2001.03622"},{"key":"17","doi-asserted-by":"publisher","unstructured":"Guang Hao Low and Isaac L Chuang. Hamiltonian simulation by uniform spectral amplification. arXiv preprint arXiv:1707.05391, 2017. 10.48550\/arXiv.1707.05391.","DOI":"10.48550\/arXiv.1707.05391"},{"key":"18","doi-asserted-by":"publisher","unstructured":"Guang Hao Low and Isaac L Chuang. Hamiltonian simulation by qubitization. Quantum, 3: 163, 2019. 10.22331\/q-2019-07-12-163.","DOI":"10.22331\/q-2019-07-12-163"},{"key":"19","doi-asserted-by":"publisher","unstructured":"Adri\u00e1n P\u00e9rez-Salinas, Alba Cervera-Lierta, Elies Gil-Fuster, and Jos\u00e9 I Latorre. Data re-uploading for a universal quantum classifier. Quantum, 4: 226, 2020. 10.22331\/q-2020-02-06-226.","DOI":"10.22331\/q-2020-02-06-226"},{"key":"20","doi-asserted-by":"publisher","unstructured":"Martin Plesch and Vladim\u00edr Bu\u017eek. Efficient compression of quantum information. Physical Review A, 81 (3): 032317, 2010. 10.1103\/PhysRevA.81.032317.","DOI":"10.1103\/PhysRevA.81.032317"},{"key":"21","doi-asserted-by":"publisher","unstructured":"Navneeth Ramakrishnan, Raban Iten, Volkher B. Scholz, and Mario Berta. Computing quantum channel capacities. IEEE Transactions on Information Theory, 67 (2): 946\u2013960, 2021. 10.1109\/TIT.2020.3034471.","DOI":"10.1109\/TIT.2020.3034471"},{"key":"22","doi-asserted-by":"publisher","unstructured":"Lee A Rozema, Dylan H Mahler, Alex Hayat, Peter S Turner, and Aephraim M Steinberg. Quantum data compression of a qubit ensemble. Physical Review Letters, 113 (16): 160504, 2014. 10.1103\/PhysRevLett.113.160504.","DOI":"10.1103\/PhysRevLett.113.160504"},{"key":"23","doi-asserted-by":"publisher","unstructured":"Sina Salek, Daniela Cadamuro, Philipp Kammerlander, and Karoline Wiesner. Quantum rate-distortion coding of relevant information. IEEE Transactions on Information Theory, 65 (4): 2603\u20132613, 2019. 10.1109\/TIT.2018.2878412.","DOI":"10.1109\/TIT.2018.2878412"},{"key":"24","doi-asserted-by":"publisher","unstructured":"Maria Schuld. Supervised quantum machine learning models are kernel methods. arXiv preprint arXiv:2101.11020, 2021. 10.48550\/arXiv.2101.11020.","DOI":"10.48550\/arXiv.2101.11020"},{"key":"25","doi-asserted-by":"publisher","unstructured":"Maria Schuld and Nathan Killoran. Quantum machine learning in feature Hilbert spaces. Physical Review Letters, 122 (4): 040504, 2019. 10.1103\/PhysRevLett.122.040504.","DOI":"10.1103\/PhysRevLett.122.040504"},{"key":"26","doi-asserted-by":"publisher","unstructured":"Maria Schuld, Ilya Sinayskiy, and Francesco Petruccione. An introduction to quantum machine learning. Contemporary Physics, 56 (2): 172\u2013185, 2015. 10.1080\/00107514.2014.964942.","DOI":"10.1080\/00107514.2014.964942"},{"key":"27","doi-asserted-by":"publisher","unstructured":"Ravid Shwartz-Ziv and Naftali Tishby. Opening the black box of deep neural networks via information. arXiv preprint arXiv:1703.00810, 2017. 10.48550\/arXiv.1703.00810.","DOI":"10.48550\/arXiv.1703.00810"},{"key":"28","doi-asserted-by":"publisher","unstructured":"Noam Slonim and Naftali Tishby. Document clustering using word clusters via the information bottleneck method. SIGIR &apos;00, pages 208\u2013215, New York, NY, USA, 2000. Association for Computing Machinery. ISBN 1581132263. 10.1145\/345508.345578.","DOI":"10.1145\/345508.345578"},{"key":"29","doi-asserted-by":"publisher","unstructured":"Maximilian Stark, Aizaz Shah, and Gerhard Bauch. Polar code construction using the information bottleneck method. In 2018 IEEE Wireless Communications and Networking Conference Workshops (WCNCW), pages 7\u201312, 2018. 10.1109\/WCNCW.2018.8368978.","DOI":"10.1109\/WCNCW.2018.8368978"},{"key":"30","doi-asserted-by":"publisher","unstructured":"DJ Strouse and David J. Schwab. The Deterministic Information Bottleneck. Neural Computation, 29 (6): 1611\u20131630, 06 2017. ISSN 0899-7667. 10.1162\/NECO_a_00961.","DOI":"10.1162\/NECO_a_00961"},{"key":"31","doi-asserted-by":"publisher","unstructured":"N. Tishby, F. C. Pereira, and W. Bialek. The information bottleneck method. In The 37th annual Allerton Conference on Communication, Control, and Computing, pages 368\u2013377. Univ. Illinois Press, 1999. 10.48550\/arXiv.physics\/0004057.","DOI":"10.48550\/arXiv.physics\/0004057"},{"key":"32","doi-asserted-by":"publisher","unstructured":"Naftali Tishby and Noga Zaslavsky. Deep learning and the information bottleneck principle. In 2015 IEEE information theory workshop (ITW), pages 1\u20135. IEEE, 2015. 10.1109\/ITW.2015.7133169.","DOI":"10.1109\/ITW.2015.7133169"},{"key":"33","doi-asserted-by":"publisher","unstructured":"Peter Wittek. Quantum machine learning: what quantum computing means to data mining. Academic Press, 2014. 10.1016\/C2013-0-19170-2.","DOI":"10.1016\/C2013-0-19170-2"},{"key":"34","doi-asserted-by":"publisher","unstructured":"Yuxiang Yang, Giulio Chiribella, and Daniel Ebler. Efficient quantum compression for ensembles of identically prepared mixed states. Physical Review Letters, 116 (8): 080501, 2016a. 10.1103\/PhysRevLett.116.080501.","DOI":"10.1103\/PhysRevLett.116.080501"},{"key":"35","doi-asserted-by":"publisher","unstructured":"Yuxiang Yang, Giulio Chiribella, and Masahito Hayashi. Optimal compression for identically prepared qubit states. Phys. Rev. Lett., 117: 090502, Aug 2016b. 10.1103\/PhysRevLett.117.090502.","DOI":"10.1103\/PhysRevLett.117.090502"},{"key":"36","doi-asserted-by":"publisher","unstructured":"Yuxiang Yang, Ge Bai, Giulio Chiribella, and Masahito Hayashi. Compression for quantum population coding. IEEE Transactions on Information Theory, 64 (7): 4766\u20134783, 2018a. 10.1109\/TIT.2017.2788407.","DOI":"10.1109\/TIT.2017.2788407"},{"key":"37","doi-asserted-by":"publisher","unstructured":"Yuxiang Yang, Giulio Chiribella, and Masahito Hayashi. Quantum stopwatch: how to store time in a quantum memory. Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences, 474 (2213): 20170773, 2018b. 10.1098\/rspa.2017.0773.","DOI":"10.1098\/rspa.2017.0773"}],"container-title":["Quantum"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/quantum-journal.org\/papers\/q-2023-03-02-936\/pdf\/","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2023,3,2]],"date-time":"2023-03-02T17:05:12Z","timestamp":1677776712000},"score":1,"resource":{"primary":{"URL":"https:\/\/quantum-journal.org\/papers\/q-2023-03-02-936\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,3,2]]},"references-count":38,"URL":"https:\/\/doi.org\/10.22331\/q-2023-03-02-936","archive":["CLOCKSS"],"relation":{},"ISSN":["2521-327X"],"issn-type":[{"value":"2521-327X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,3,2]]},"article-number":"936"}}