A simple randomized algorithm for sequential prediction of ergodic time series
We present a simple randomized procedure for the prediction of a binary sequence. The algorithm uses ideas from previous developments of the theory of the prediction of individual sequences. We show that if the sequence is a realization of a stationary and ergodic random process then the average num...
Gespeichert in:
| Veröffentlicht in: | IEEE transactions on information theory 1999-11, Vol.45 (7), p.2642-2650 |
|---|---|
| Hauptverfasser: | , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 2650 |
|---|---|
| container_issue | 7 |
| container_start_page | 2642 |
| container_title | IEEE transactions on information theory |
| container_volume | 45 |
| creator | Gyorfi, L. Lugosi, G. Morvai, G. |
| description | We present a simple randomized procedure for the prediction of a binary sequence. The algorithm uses ideas from previous developments of the theory of the prediction of individual sequences. We show that if the sequence is a realization of a stationary and ergodic random process then the average number of mistakes converges, almost surely, to that of the optimum, given by the Bayes predictor. The desirable finite-sample properties of the predictor are illustrated by its performance for Markov processes. In such cases the predictor exhibits near-optimal behavior even without knowing the order of the Markov process. Prediction with side information is also considered. |
| doi_str_mv | 10.1109/18.796420 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_RIE</sourceid><recordid>TN_cdi_ieee_primary_796420</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>796420</ieee_id><sourcerecordid>46533086</sourcerecordid><originalsourceid>FETCH-LOGICAL-c371t-44d27278d0b3124fb450c4485a7c585e100de039b099036df1364139f3aae1b83</originalsourceid><addsrcrecordid>eNp90T1PwzAQBmALgUT5GFiZLAYQQ4ovthN7rCq-pAoWmCMnuRRXSRzsdIBfj6tUDAxMp9M9Ot3pJeQC2ByA6TtQ81xnImUHZAZS5onOpDgkM8ZAJVoIdUxOQtjEVkhIZ-RlQYPthhapN33tOvuNNTXt2nk7fnS0cZ4G_NxiP1rT0sFjbavRup66hqJfu9jS0XYYlbcYzshRY9qA5_t6St4f7t-WT8nq9fF5uVglFc9hTISo0zzNVc1KDqloSiFZFY-TJq-kkgiM1ci4LpnWjGd1AzwTwHXDjUEoFT8lN9Pewbt4XRiLzoYK29b06Lah0KA15EplUV7_K1OVsTzTOsKrP3Djtr6PXxSgpU45g9222wlV3oXgsSkGbzvjvwpgxS6AAlQxBRDt5WQtIv66_fAH5_p-nA</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>195923016</pqid></control><display><type>article</type><title>A simple randomized algorithm for sequential prediction of ergodic time series</title><source>IEEE Electronic Library (IEL)</source><creator>Gyorfi, L. ; Lugosi, G. ; Morvai, G.</creator><creatorcontrib>Gyorfi, L. ; Lugosi, G. ; Morvai, G.</creatorcontrib><description>We present a simple randomized procedure for the prediction of a binary sequence. The algorithm uses ideas from previous developments of the theory of the prediction of individual sequences. We show that if the sequence is a realization of a stationary and ergodic random process then the average number of mistakes converges, almost surely, to that of the optimum, given by the Bayes predictor. The desirable finite-sample properties of the predictor are illustrated by its performance for Markov processes. In such cases the predictor exhibits near-optimal behavior even without knowing the order of the Markov process. Prediction with side information is also considered.</description><identifier>ISSN: 0018-9448</identifier><identifier>EISSN: 1557-9654</identifier><identifier>DOI: 10.1109/18.796420</identifier><identifier>CODEN: IETTAW</identifier><language>eng</language><publisher>New York: IEEE</publisher><subject>Algorithms ; Bayesian analysis ; Binary sequences ; Ergodic processes ; Information technology ; Information theory ; Markov processes ; Optimization ; Random processes ; Time series</subject><ispartof>IEEE transactions on information theory, 1999-11, Vol.45 (7), p.2642-2650</ispartof><rights>Copyright Institute of Electrical and Electronics Engineers, Inc. (IEEE) Nov 1999</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c371t-44d27278d0b3124fb450c4485a7c585e100de039b099036df1364139f3aae1b83</citedby><cites>FETCH-LOGICAL-c371t-44d27278d0b3124fb450c4485a7c585e100de039b099036df1364139f3aae1b83</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/796420$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>314,776,780,792,27901,27902,54733</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/796420$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Gyorfi, L.</creatorcontrib><creatorcontrib>Lugosi, G.</creatorcontrib><creatorcontrib>Morvai, G.</creatorcontrib><title>A simple randomized algorithm for sequential prediction of ergodic time series</title><title>IEEE transactions on information theory</title><addtitle>TIT</addtitle><description>We present a simple randomized procedure for the prediction of a binary sequence. The algorithm uses ideas from previous developments of the theory of the prediction of individual sequences. We show that if the sequence is a realization of a stationary and ergodic random process then the average number of mistakes converges, almost surely, to that of the optimum, given by the Bayes predictor. The desirable finite-sample properties of the predictor are illustrated by its performance for Markov processes. In such cases the predictor exhibits near-optimal behavior even without knowing the order of the Markov process. Prediction with side information is also considered.</description><subject>Algorithms</subject><subject>Bayesian analysis</subject><subject>Binary sequences</subject><subject>Ergodic processes</subject><subject>Information technology</subject><subject>Information theory</subject><subject>Markov processes</subject><subject>Optimization</subject><subject>Random processes</subject><subject>Time series</subject><issn>0018-9448</issn><issn>1557-9654</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>1999</creationdate><recordtype>article</recordtype><sourceid>RIE</sourceid><recordid>eNp90T1PwzAQBmALgUT5GFiZLAYQQ4ovthN7rCq-pAoWmCMnuRRXSRzsdIBfj6tUDAxMp9M9Ot3pJeQC2ByA6TtQ81xnImUHZAZS5onOpDgkM8ZAJVoIdUxOQtjEVkhIZ-RlQYPthhapN33tOvuNNTXt2nk7fnS0cZ4G_NxiP1rT0sFjbavRup66hqJfu9jS0XYYlbcYzshRY9qA5_t6St4f7t-WT8nq9fF5uVglFc9hTISo0zzNVc1KDqloSiFZFY-TJq-kkgiM1ci4LpnWjGd1AzwTwHXDjUEoFT8lN9Pewbt4XRiLzoYK29b06Lah0KA15EplUV7_K1OVsTzTOsKrP3Djtr6PXxSgpU45g9222wlV3oXgsSkGbzvjvwpgxS6AAlQxBRDt5WQtIv66_fAH5_p-nA</recordid><startdate>19991101</startdate><enddate>19991101</enddate><creator>Gyorfi, L.</creator><creator>Lugosi, G.</creator><creator>Morvai, G.</creator><general>IEEE</general><general>The Institute of Electrical and Electronics Engineers, Inc. (IEEE)</general><scope>RIA</scope><scope>RIE</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7SC</scope><scope>7SP</scope><scope>8FD</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope><scope>F28</scope><scope>FR3</scope></search><sort><creationdate>19991101</creationdate><title>A simple randomized algorithm for sequential prediction of ergodic time series</title><author>Gyorfi, L. ; Lugosi, G. ; Morvai, G.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c371t-44d27278d0b3124fb450c4485a7c585e100de039b099036df1364139f3aae1b83</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>1999</creationdate><topic>Algorithms</topic><topic>Bayesian analysis</topic><topic>Binary sequences</topic><topic>Ergodic processes</topic><topic>Information technology</topic><topic>Information theory</topic><topic>Markov processes</topic><topic>Optimization</topic><topic>Random processes</topic><topic>Time series</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Gyorfi, L.</creatorcontrib><creatorcontrib>Lugosi, G.</creatorcontrib><creatorcontrib>Morvai, G.</creatorcontrib><collection>IEEE All-Society Periodicals Package (ASPP) 1998-Present</collection><collection>IEEE Electronic Library (IEL)</collection><collection>CrossRef</collection><collection>Computer and Information Systems Abstracts</collection><collection>Electronics & Communications Abstracts</collection><collection>Technology Research Database</collection><collection>ProQuest Computer Science Collection</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><collection>ANTE: Abstracts in New Technology & Engineering</collection><collection>Engineering Research Database</collection><jtitle>IEEE transactions on information theory</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Gyorfi, L.</au><au>Lugosi, G.</au><au>Morvai, G.</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>A simple randomized algorithm for sequential prediction of ergodic time series</atitle><jtitle>IEEE transactions on information theory</jtitle><stitle>TIT</stitle><date>1999-11-01</date><risdate>1999</risdate><volume>45</volume><issue>7</issue><spage>2642</spage><epage>2650</epage><pages>2642-2650</pages><issn>0018-9448</issn><eissn>1557-9654</eissn><coden>IETTAW</coden><abstract>We present a simple randomized procedure for the prediction of a binary sequence. The algorithm uses ideas from previous developments of the theory of the prediction of individual sequences. We show that if the sequence is a realization of a stationary and ergodic random process then the average number of mistakes converges, almost surely, to that of the optimum, given by the Bayes predictor. The desirable finite-sample properties of the predictor are illustrated by its performance for Markov processes. In such cases the predictor exhibits near-optimal behavior even without knowing the order of the Markov process. Prediction with side information is also considered.</abstract><cop>New York</cop><pub>IEEE</pub><doi>10.1109/18.796420</doi><tpages>9</tpages><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISSN: 0018-9448 |
| ispartof | IEEE transactions on information theory, 1999-11, Vol.45 (7), p.2642-2650 |
| issn | 0018-9448 1557-9654 |
| language | eng |
| recordid | cdi_ieee_primary_796420 |
| source | IEEE Electronic Library (IEL) |
| subjects | Algorithms Bayesian analysis Binary sequences Ergodic processes Information technology Information theory Markov processes Optimization Random processes Time series |
| title | A simple randomized algorithm for sequential prediction of ergodic time series |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-30T13%3A14%3A47IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_RIE&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=A%20simple%20randomized%20algorithm%20for%20sequential%20prediction%20of%20ergodic%20time%20series&rft.jtitle=IEEE%20transactions%20on%20information%20theory&rft.au=Gyorfi,%20L.&rft.date=1999-11-01&rft.volume=45&rft.issue=7&rft.spage=2642&rft.epage=2650&rft.pages=2642-2650&rft.issn=0018-9448&rft.eissn=1557-9654&rft.coden=IETTAW&rft_id=info:doi/10.1109/18.796420&rft_dat=%3Cproquest_RIE%3E46533086%3C/proquest_RIE%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=195923016&rft_id=info:pmid/&rft_ieee_id=796420&rfr_iscdi=true |