A Meta-Learning Based Precoder Optimization Framework for Rate-Splitting Multiple Access

In this letter, we propose the use of a meta-learning based precoder optimization framework to directly optimize the Rate-Splitting Multiple Access (RSMA) precoders with partial Channel State Information at the Transmitter (CSIT). By exploiting the overfitting of the compact neural network to maximi...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Loli, Rafael Cerna, Clerckx, Bruno
Format:	Artikel
Sprache:	eng
Schlagworte:	Computer Science - Information Theory Computer Science - Learning Mathematics - Information Theory
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	Loli, Rafael Cerna Clerckx, Bruno
description	In this letter, we propose the use of a meta-learning based precoder optimization framework to directly optimize the Rate-Splitting Multiple Access (RSMA) precoders with partial Channel State Information at the Transmitter (CSIT). By exploiting the overfitting of the compact neural network to maximize the explicit Average Sum-Rate (ASR) expression, we effectively bypass the need for any other training data while minimizing the total running time. Numerical results reveal that the meta-learning based solution achieves similar ASR performance to conventional precoder optimization in medium-scale scenarios, and significantly outperforms sub-optimal low complexity precoder algorithms in the large-scale regime.
doi_str_mv	10.48550/arxiv.2307.08822
format	Article
fullrecord	<record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2307_08822</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2307_08822</sourcerecordid><originalsourceid>FETCH-LOGICAL-a672-80443f15ccf90fb86a551268c509e58eda0ed7b413659e00019403f8644447433</originalsourceid><addsrcrecordid>eNotz71OwzAUBWAvDKjwAEz1CzjcxHbijKGigJSqiHZgi26da2SRPznm9-mhhbOc6RzpY-wqhUQZreEaw6d_TzIJRQLGZNk5e674hiKKmjAMfnjhNzhTyx8D2bGlwLdT9L3_xujHga8D9vQxhlfuxsCfMJLYTZ2P8TjcvHXRTx3xylqa5wt25rCb6fK_F2y_vt2v7kW9vXtYVbXAvMiEAaWkS7W1rgR3MDlqnWa5sRpK0oZaBGqLg0plrksCgLRUIJ3J1W8KJeWCLf9uT7RmCr7H8NUcic2JKH8Ag51K_Q</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>A Meta-Learning Based Precoder Optimization Framework for Rate-Splitting Multiple Access</title><source>arXiv.org</source><creator>Loli, Rafael Cerna ; Clerckx, Bruno</creator><creatorcontrib>Loli, Rafael Cerna ; Clerckx, Bruno</creatorcontrib><description>In this letter, we propose the use of a meta-learning based precoder optimization framework to directly optimize the Rate-Splitting Multiple Access (RSMA) precoders with partial Channel State Information at the Transmitter (CSIT). By exploiting the overfitting of the compact neural network to maximize the explicit Average Sum-Rate (ASR) expression, we effectively bypass the need for any other training data while minimizing the total running time. Numerical results reveal that the meta-learning based solution achieves similar ASR performance to conventional precoder optimization in medium-scale scenarios, and significantly outperforms sub-optimal low complexity precoder algorithms in the large-scale regime.</description><identifier>DOI: 10.48550/arxiv.2307.08822</identifier><language>eng</language><subject>Computer Science - Information Theory ; Computer Science - Learning ; Mathematics - Information Theory</subject><creationdate>2023-07</creationdate><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,777,882</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2307.08822$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2307.08822$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Loli, Rafael Cerna</creatorcontrib><creatorcontrib>Clerckx, Bruno</creatorcontrib><title>A Meta-Learning Based Precoder Optimization Framework for Rate-Splitting Multiple Access</title><description>In this letter, we propose the use of a meta-learning based precoder optimization framework to directly optimize the Rate-Splitting Multiple Access (RSMA) precoders with partial Channel State Information at the Transmitter (CSIT). By exploiting the overfitting of the compact neural network to maximize the explicit Average Sum-Rate (ASR) expression, we effectively bypass the need for any other training data while minimizing the total running time. Numerical results reveal that the meta-learning based solution achieves similar ASR performance to conventional precoder optimization in medium-scale scenarios, and significantly outperforms sub-optimal low complexity precoder algorithms in the large-scale regime.</description><subject>Computer Science - Information Theory</subject><subject>Computer Science - Learning</subject><subject>Mathematics - Information Theory</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotz71OwzAUBWAvDKjwAEz1CzjcxHbijKGigJSqiHZgi26da2SRPznm9-mhhbOc6RzpY-wqhUQZreEaw6d_TzIJRQLGZNk5e674hiKKmjAMfnjhNzhTyx8D2bGlwLdT9L3_xujHga8D9vQxhlfuxsCfMJLYTZ2P8TjcvHXRTx3xylqa5wt25rCb6fK_F2y_vt2v7kW9vXtYVbXAvMiEAaWkS7W1rgR3MDlqnWa5sRpK0oZaBGqLg0plrksCgLRUIJ3J1W8KJeWCLf9uT7RmCr7H8NUcic2JKH8Ag51K_Q</recordid><startdate>20230717</startdate><enddate>20230717</enddate><creator>Loli, Rafael Cerna</creator><creator>Clerckx, Bruno</creator><scope>AKY</scope><scope>AKZ</scope><scope>GOX</scope></search><sort><creationdate>20230717</creationdate><title>A Meta-Learning Based Precoder Optimization Framework for Rate-Splitting Multiple Access</title><author>Loli, Rafael Cerna ; Clerckx, Bruno</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a672-80443f15ccf90fb86a551268c509e58eda0ed7b413659e00019403f8644447433</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Computer Science - Information Theory</topic><topic>Computer Science - Learning</topic><topic>Mathematics - Information Theory</topic><toplevel>online_resources</toplevel><creatorcontrib>Loli, Rafael Cerna</creatorcontrib><creatorcontrib>Clerckx, Bruno</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>Loli, Rafael Cerna</au><au>Clerckx, Bruno</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>A Meta-Learning Based Precoder Optimization Framework for Rate-Splitting Multiple Access</atitle><date>2023-07-17</date><risdate>2023</risdate><abstract>In this letter, we propose the use of a meta-learning based precoder optimization framework to directly optimize the Rate-Splitting Multiple Access (RSMA) precoders with partial Channel State Information at the Transmitter (CSIT). By exploiting the overfitting of the compact neural network to maximize the explicit Average Sum-Rate (ASR) expression, we effectively bypass the need for any other training data while minimizing the total running time. Numerical results reveal that the meta-learning based solution achieves similar ASR performance to conventional precoder optimization in medium-scale scenarios, and significantly outperforms sub-optimal low complexity precoder algorithms in the large-scale regime.</abstract><doi>10.48550/arxiv.2307.08822</doi><oa>free_for_read</oa></addata></record>
fulltext	fulltext_linktorsrc
identifier	DOI: 10.48550/arxiv.2307.08822
ispartof
issn
language	eng
recordid	cdi_arxiv_primary_2307_08822
source	arXiv.org
subjects	Computer Science - Information Theory Computer Science - Learning Mathematics - Information Theory
title	A Meta-Learning Based Precoder Optimization Framework for Rate-Splitting Multiple Access
url	https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-18T05%3A05%3A50IST&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=A%20Meta-Learning%20Based%20Precoder%20Optimization%20Framework%20for%20Rate-Splitting%20Multiple%20Access&rft.au=Loli,%20Rafael%20Cerna&rft.date=2023-07-17&rft_id=info:doi/10.48550/arxiv.2307.08822&rft_dat=%3Carxiv_GOX%3E2307_08822%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