Online Forecasting Matrix Factorization

In this paper the problem of forecasting high dimensional time series is considered. Such time series can be modeled as matrices where each column denotes a measurement. In addition, when missing values are present, low rank matrix factorization approaches are suitable for predicting future values....

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Gultekin, San, Paisley, John
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 Gultekin, San
Paisley, John
description In this paper the problem of forecasting high dimensional time series is considered. Such time series can be modeled as matrices where each column denotes a measurement. In addition, when missing values are present, low rank matrix factorization approaches are suitable for predicting future values. This paper formally defines and analyzes the forecasting problem in the online setting, i.e. where the data arrives as a stream and only a single pass is allowed. We present and analyze novel matrix factorization techniques which can learn low-dimensional embeddings effectively in an online manner. Based on these embeddings a recursive minimum mean square error estimator is derived, which learns an autoregressive model on them. Experiments with two real datasets with tens of millions of measurements show the benefits of the proposed approach.
doi_str_mv 10.48550/arxiv.1712.08734
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_1712_08734</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>1712_08734</sourcerecordid><originalsourceid>FETCH-LOGICAL-a674-47a41ce5ed2029180c8b9286a252244d122f5a166aabf384f54a8058534da27d3</originalsourceid><addsrcrecordid>eNotzrEOgjAUQNEuDgb9ACfZnMD29ZXW0RhREwwLO3lCMU0UTCVG_XojOt3t5jA2EzxGoxRfkn-6Ryy0gJgbLXHMFnl7ca0N087biu69a8_hkXrvnmFKVd9596bede2EjRq63O3034AV6bbY7KMs3x026yyiRGOEmlBUVtkaOKyE4ZU5rcAkBAoAsRYAjSKRJESnRhpsFJLhyiiJNYGuZcDmv-0gLW_eXcm_yq-4HMTyA39HOe8</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Online Forecasting Matrix Factorization</title><source>arXiv.org</source><creator>Gultekin, San ; Paisley, John</creator><creatorcontrib>Gultekin, San ; Paisley, John</creatorcontrib><description>In this paper the problem of forecasting high dimensional time series is considered. Such time series can be modeled as matrices where each column denotes a measurement. In addition, when missing values are present, low rank matrix factorization approaches are suitable for predicting future values. This paper formally defines and analyzes the forecasting problem in the online setting, i.e. where the data arrives as a stream and only a single pass is allowed. We present and analyze novel matrix factorization techniques which can learn low-dimensional embeddings effectively in an online manner. Based on these embeddings a recursive minimum mean square error estimator is derived, which learns an autoregressive model on them. Experiments with two real datasets with tens of millions of measurements show the benefits of the proposed approach.</description><identifier>DOI: 10.48550/arxiv.1712.08734</identifier><language>eng</language><subject>Computer Science - Learning</subject><creationdate>2017-12</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>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,780,885</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/1712.08734$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.1712.08734$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Gultekin, San</creatorcontrib><creatorcontrib>Paisley, John</creatorcontrib><title>Online Forecasting Matrix Factorization</title><description>In this paper the problem of forecasting high dimensional time series is considered. Such time series can be modeled as matrices where each column denotes a measurement. In addition, when missing values are present, low rank matrix factorization approaches are suitable for predicting future values. This paper formally defines and analyzes the forecasting problem in the online setting, i.e. where the data arrives as a stream and only a single pass is allowed. We present and analyze novel matrix factorization techniques which can learn low-dimensional embeddings effectively in an online manner. Based on these embeddings a recursive minimum mean square error estimator is derived, which learns an autoregressive model on them. Experiments with two real datasets with tens of millions of measurements show the benefits of the proposed approach.</description><subject>Computer Science - Learning</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2017</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotzrEOgjAUQNEuDgb9ACfZnMD29ZXW0RhREwwLO3lCMU0UTCVG_XojOt3t5jA2EzxGoxRfkn-6Ryy0gJgbLXHMFnl7ca0N087biu69a8_hkXrvnmFKVd9596bede2EjRq63O3034AV6bbY7KMs3x026yyiRGOEmlBUVtkaOKyE4ZU5rcAkBAoAsRYAjSKRJESnRhpsFJLhyiiJNYGuZcDmv-0gLW_eXcm_yq-4HMTyA39HOe8</recordid><startdate>20171223</startdate><enddate>20171223</enddate><creator>Gultekin, San</creator><creator>Paisley, John</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20171223</creationdate><title>Online Forecasting Matrix Factorization</title><author>Gultekin, San ; Paisley, John</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a674-47a41ce5ed2029180c8b9286a252244d122f5a166aabf384f54a8058534da27d3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2017</creationdate><topic>Computer Science - Learning</topic><toplevel>online_resources</toplevel><creatorcontrib>Gultekin, San</creatorcontrib><creatorcontrib>Paisley, John</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Gultekin, San</au><au>Paisley, John</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Online Forecasting Matrix Factorization</atitle><date>2017-12-23</date><risdate>2017</risdate><abstract>In this paper the problem of forecasting high dimensional time series is considered. Such time series can be modeled as matrices where each column denotes a measurement. In addition, when missing values are present, low rank matrix factorization approaches are suitable for predicting future values. This paper formally defines and analyzes the forecasting problem in the online setting, i.e. where the data arrives as a stream and only a single pass is allowed. We present and analyze novel matrix factorization techniques which can learn low-dimensional embeddings effectively in an online manner. Based on these embeddings a recursive minimum mean square error estimator is derived, which learns an autoregressive model on them. Experiments with two real datasets with tens of millions of measurements show the benefits of the proposed approach.</abstract><doi>10.48550/arxiv.1712.08734</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.1712.08734
ispartof
issn
language eng
recordid cdi_arxiv_primary_1712_08734
source arXiv.org
subjects Computer Science - Learning
title Online Forecasting Matrix Factorization
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-03T10%3A06%3A29IST&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=Online%20Forecasting%20Matrix%20Factorization&rft.au=Gultekin,%20San&rft.date=2017-12-23&rft_id=info:doi/10.48550/arxiv.1712.08734&rft_dat=%3Carxiv_GOX%3E1712_08734%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