Variational Autoencoders for Precoding Matrices with High Spectral Efficiency
Neural networks are used for channel decoding, channel detection, channel evaluation, and resource management in multi-input and multi-output (MIMO) wireless communication systems. In this paper, we consider the problem of finding precoding matrices with high spectral efficiency (SE) using variation...
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | |
|---|---|
| container_issue | |
| container_start_page | |
| container_title | |
| container_volume | |
| creator | Bobrov, Evgeny Markov, Alexander Panchenko, Sviatoslav Vetrov, Dmitry |
| description | Neural networks are used for channel decoding, channel detection, channel
evaluation, and resource management in multi-input and multi-output (MIMO)
wireless communication systems. In this paper, we consider the problem of
finding precoding matrices with high spectral efficiency (SE) using variational
autoencoder (VAE). We propose a computationally efficient algorithm for
sampling precoding matrices with minimal loss of quality compared to the
optimal precoding. In addition to VAE, we use the conditional variational
autoencoder (CVAE) to build a unified generative model. Both of these methods
are able to reconstruct the distribution of precoding matrices of high SE by
sampling latent variables. This distribution obtained using VAE and CVAE
methods is described in the literature for the first time. |
| doi_str_mv | 10.48550/arxiv.2111.15626 |
| format | Article |
| fullrecord | <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2111_15626</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2111_15626</sourcerecordid><originalsourceid>FETCH-LOGICAL-a676-9fd6f252ff0a12ccf7afdccfba6b302c38d2c77e18b971714f4028ab2a7243683</originalsourceid><addsrcrecordid>eNotj8tuwjAQRb1hUUE_oKv6B5La48Q2S4RoqQSiUlG30cTxwEg0QU764O-b0q6O7uJc6Qhxp1Ve-LJUD5i--TMHrXWuSwv2RmzfMDEO3LV4kouPoYtt6JqYekldki8pjovbg9zikDjEXn7xcJRrPhzl6zmGIY3aiogDj-JlJiaEpz7e_nMq9o-r_XKdbXZPz8vFJkPrbDanxhKUQKRQQwjkkJoRNdraKAjGNxCci9rXc6edLqhQ4LEGdFAY681U3P_dXnuqc-J3TJfqt6u6dpkfw9lJQQ</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Variational Autoencoders for Precoding Matrices with High Spectral Efficiency</title><source>arXiv.org</source><creator>Bobrov, Evgeny ; Markov, Alexander ; Panchenko, Sviatoslav ; Vetrov, Dmitry</creator><creatorcontrib>Bobrov, Evgeny ; Markov, Alexander ; Panchenko, Sviatoslav ; Vetrov, Dmitry</creatorcontrib><description>Neural networks are used for channel decoding, channel detection, channel
evaluation, and resource management in multi-input and multi-output (MIMO)
wireless communication systems. In this paper, we consider the problem of
finding precoding matrices with high spectral efficiency (SE) using variational
autoencoder (VAE). We propose a computationally efficient algorithm for
sampling precoding matrices with minimal loss of quality compared to the
optimal precoding. In addition to VAE, we use the conditional variational
autoencoder (CVAE) to build a unified generative model. Both of these methods
are able to reconstruct the distribution of precoding matrices of high SE by
sampling latent variables. This distribution obtained using VAE and CVAE
methods is described in the literature for the first time.</description><identifier>DOI: 10.48550/arxiv.2111.15626</identifier><language>eng</language><subject>Computer Science - Artificial Intelligence ; Computer Science - Information Theory ; Mathematics - Information Theory</subject><creationdate>2021-11</creationdate><rights>http://creativecommons.org/licenses/by/4.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,780,885</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2111.15626$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2111.15626$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Bobrov, Evgeny</creatorcontrib><creatorcontrib>Markov, Alexander</creatorcontrib><creatorcontrib>Panchenko, Sviatoslav</creatorcontrib><creatorcontrib>Vetrov, Dmitry</creatorcontrib><title>Variational Autoencoders for Precoding Matrices with High Spectral Efficiency</title><description>Neural networks are used for channel decoding, channel detection, channel
evaluation, and resource management in multi-input and multi-output (MIMO)
wireless communication systems. In this paper, we consider the problem of
finding precoding matrices with high spectral efficiency (SE) using variational
autoencoder (VAE). We propose a computationally efficient algorithm for
sampling precoding matrices with minimal loss of quality compared to the
optimal precoding. In addition to VAE, we use the conditional variational
autoencoder (CVAE) to build a unified generative model. Both of these methods
are able to reconstruct the distribution of precoding matrices of high SE by
sampling latent variables. This distribution obtained using VAE and CVAE
methods is described in the literature for the first time.</description><subject>Computer Science - Artificial Intelligence</subject><subject>Computer Science - Information Theory</subject><subject>Mathematics - Information Theory</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotj8tuwjAQRb1hUUE_oKv6B5La48Q2S4RoqQSiUlG30cTxwEg0QU764O-b0q6O7uJc6Qhxp1Ve-LJUD5i--TMHrXWuSwv2RmzfMDEO3LV4kouPoYtt6JqYekldki8pjovbg9zikDjEXn7xcJRrPhzl6zmGIY3aiogDj-JlJiaEpz7e_nMq9o-r_XKdbXZPz8vFJkPrbDanxhKUQKRQQwjkkJoRNdraKAjGNxCci9rXc6edLqhQ4LEGdFAY681U3P_dXnuqc-J3TJfqt6u6dpkfw9lJQQ</recordid><startdate>20211123</startdate><enddate>20211123</enddate><creator>Bobrov, Evgeny</creator><creator>Markov, Alexander</creator><creator>Panchenko, Sviatoslav</creator><creator>Vetrov, Dmitry</creator><scope>AKY</scope><scope>AKZ</scope><scope>GOX</scope></search><sort><creationdate>20211123</creationdate><title>Variational Autoencoders for Precoding Matrices with High Spectral Efficiency</title><author>Bobrov, Evgeny ; Markov, Alexander ; Panchenko, Sviatoslav ; Vetrov, Dmitry</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a676-9fd6f252ff0a12ccf7afdccfba6b302c38d2c77e18b971714f4028ab2a7243683</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>Computer Science - Artificial Intelligence</topic><topic>Computer Science - Information Theory</topic><topic>Mathematics - Information Theory</topic><toplevel>online_resources</toplevel><creatorcontrib>Bobrov, Evgeny</creatorcontrib><creatorcontrib>Markov, Alexander</creatorcontrib><creatorcontrib>Panchenko, Sviatoslav</creatorcontrib><creatorcontrib>Vetrov, Dmitry</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv Mathematics</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Bobrov, Evgeny</au><au>Markov, Alexander</au><au>Panchenko, Sviatoslav</au><au>Vetrov, Dmitry</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Variational Autoencoders for Precoding Matrices with High Spectral Efficiency</atitle><date>2021-11-23</date><risdate>2021</risdate><abstract>Neural networks are used for channel decoding, channel detection, channel
evaluation, and resource management in multi-input and multi-output (MIMO)
wireless communication systems. In this paper, we consider the problem of
finding precoding matrices with high spectral efficiency (SE) using variational
autoencoder (VAE). We propose a computationally efficient algorithm for
sampling precoding matrices with minimal loss of quality compared to the
optimal precoding. In addition to VAE, we use the conditional variational
autoencoder (CVAE) to build a unified generative model. Both of these methods
are able to reconstruct the distribution of precoding matrices of high SE by
sampling latent variables. This distribution obtained using VAE and CVAE
methods is described in the literature for the first time.</abstract><doi>10.48550/arxiv.2111.15626</doi><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | DOI: 10.48550/arxiv.2111.15626 |
| ispartof | |
| issn | |
| language | eng |
| recordid | cdi_arxiv_primary_2111_15626 |
| source | arXiv.org |
| subjects | Computer Science - Artificial Intelligence Computer Science - Information Theory Mathematics - Information Theory |
| title | Variational Autoencoders for Precoding Matrices with High Spectral Efficiency |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-12T09%3A33%3A01IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Variational%20Autoencoders%20for%20Precoding%20Matrices%20with%20High%20Spectral%20Efficiency&rft.au=Bobrov,%20Evgeny&rft.date=2021-11-23&rft_id=info:doi/10.48550/arxiv.2111.15626&rft_dat=%3Carxiv_GOX%3E2111_15626%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true |