File Download
  Links for fulltext
     (May Require Subscription)
Supplementary

Article: Efficient algorithms for quantum information bottleneck

TitleEfficient algorithms for quantum information bottleneck
Authors
Issue Date2-Mar-2023
PublisherVerein zur Förderung des Open Access Publizierens in den Quantenwissenschaften
Citation
Quantum, 2023, v. 7 How to Cite?
Abstract

The ability to extract relevant information is critical to learning. An ingenious approach as such is the information bottleneck, an optimi-sation 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 infor-mation regarding quantum systems. Here we address this by proposing a new and general algorithm for the quantum generalisation of in-formation 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 infor-mation bottleneck, an important variant of the original information bottleneck problem. No-tably, we discover that a quantum system can achieve strictly better performance than a clas-sical system of the same size regarding quan-tum information bottleneck, providing new vi-sion on justifying the advantage of quantum machine learning.


Persistent Identifierhttp://hdl.handle.net/10722/331490
ISSN
2023 Impact Factor: 5.1
2023 SCImago Journal Rankings: 2.562
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorHayashi, Masahito-
dc.contributor.authorYang, Yuxiang-
dc.date.accessioned2023-09-21T06:56:17Z-
dc.date.available2023-09-21T06:56:17Z-
dc.date.issued2023-03-02-
dc.identifier.citationQuantum, 2023, v. 7-
dc.identifier.issn2521-327X-
dc.identifier.urihttp://hdl.handle.net/10722/331490-
dc.description.abstract<p></p><p>The ability to extract relevant information is critical to learning. An ingenious approach as such is the information bottleneck, an optimi-sation 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 infor-mation regarding quantum systems. Here we address this by proposing a new and general algorithm for the quantum generalisation of in-formation 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 infor-mation bottleneck, an important variant of the original information bottleneck problem. No-tably, we discover that a quantum system can achieve strictly better performance than a clas-sical system of the same size regarding quan-tum information bottleneck, providing new vi-sion on justifying the advantage of quantum machine learning.<br></p>-
dc.languageeng-
dc.publisherVerein zur Förderung des Open Access Publizierens in den Quantenwissenschaften-
dc.relation.ispartofQuantum-
dc.rightsThis work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.-
dc.titleEfficient algorithms for quantum information bottleneck-
dc.typeArticle-
dc.description.naturepublished_or_final_version-
dc.identifier.doi10.22331/q-2023-03-02-936-
dc.identifier.scopuseid_2-s2.0-85159327784-
dc.identifier.volume7-
dc.identifier.eissn2521-327X-
dc.identifier.isiWOS:000958945600001-
dc.identifier.issnl2521-327X-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats