Continuous Optimization for Offline Change Point Detection and Estimation

This work explores use of novel advances in best subset selection for regression modelling via continuous optimization for offline change point detection and estimation in univariate Gaussian data sequences. The approach exploits reformulating the normal mean multiple change point model into a regul...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Reimann, Hans, Moka, Sarat, Sofronov, Georgy
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 Reimann, Hans
Moka, Sarat
Sofronov, Georgy
description This work explores use of novel advances in best subset selection for regression modelling via continuous optimization for offline change point detection and estimation in univariate Gaussian data sequences. The approach exploits reformulating the normal mean multiple change point model into a regularized statistical inverse problem enforcing sparsity. After introducing the problem statement, criteria and previous investigations via Lasso-regularization, the recently developed framework of continuous optimization for best subset selection (COMBSS) is briefly introduced and related to the problem at hand. Supervised and unsupervised perspectives are explored with the latter testing different approaches for the choice of regularization penalty parameters via the discrepancy principle and a confidence bound. The main result is an adaptation and evaluation of the COMBSS approach for offline normal mean multiple change-point detection via experimental results on simulated data for different choices of regularisation parameters. Results and future directions are discussed.
doi_str_mv 10.48550/arxiv.2407.03383
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2407_03383</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2407_03383</sourcerecordid><originalsourceid>FETCH-arxiv_primary_2407_033833</originalsourceid><addsrcrecordid>eNpjYJA0NNAzsTA1NdBPLKrILNMzMjEw1zMwNrYw5mTwdM7PK8nMK80vLVbwLyjJzM2sSizJzM9TSMsvUvBPS8vJzEtVcM5IzEtPVQjIz8wrUXBJLUlNBitJzEtRcC0G6gHr4GFgTUvMKU7lhdLcDPJuriHOHrpgS-MLioDqiirjQZbHgy03JqwCAGIoOl4</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Continuous Optimization for Offline Change Point Detection and Estimation</title><source>arXiv.org</source><creator>Reimann, Hans ; Moka, Sarat ; Sofronov, Georgy</creator><creatorcontrib>Reimann, Hans ; Moka, Sarat ; Sofronov, Georgy</creatorcontrib><description>This work explores use of novel advances in best subset selection for regression modelling via continuous optimization for offline change point detection and estimation in univariate Gaussian data sequences. The approach exploits reformulating the normal mean multiple change point model into a regularized statistical inverse problem enforcing sparsity. After introducing the problem statement, criteria and previous investigations via Lasso-regularization, the recently developed framework of continuous optimization for best subset selection (COMBSS) is briefly introduced and related to the problem at hand. Supervised and unsupervised perspectives are explored with the latter testing different approaches for the choice of regularization penalty parameters via the discrepancy principle and a confidence bound. The main result is an adaptation and evaluation of the COMBSS approach for offline normal mean multiple change-point detection via experimental results on simulated data for different choices of regularisation parameters. Results and future directions are discussed.</description><identifier>DOI: 10.48550/arxiv.2407.03383</identifier><language>eng</language><subject>Statistics - Computation ; Statistics - Machine Learning ; Statistics - Methodology</subject><creationdate>2024-07</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/2407.03383$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2407.03383$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Reimann, Hans</creatorcontrib><creatorcontrib>Moka, Sarat</creatorcontrib><creatorcontrib>Sofronov, Georgy</creatorcontrib><title>Continuous Optimization for Offline Change Point Detection and Estimation</title><description>This work explores use of novel advances in best subset selection for regression modelling via continuous optimization for offline change point detection and estimation in univariate Gaussian data sequences. The approach exploits reformulating the normal mean multiple change point model into a regularized statistical inverse problem enforcing sparsity. After introducing the problem statement, criteria and previous investigations via Lasso-regularization, the recently developed framework of continuous optimization for best subset selection (COMBSS) is briefly introduced and related to the problem at hand. Supervised and unsupervised perspectives are explored with the latter testing different approaches for the choice of regularization penalty parameters via the discrepancy principle and a confidence bound. The main result is an adaptation and evaluation of the COMBSS approach for offline normal mean multiple change-point detection via experimental results on simulated data for different choices of regularisation parameters. Results and future directions are discussed.</description><subject>Statistics - Computation</subject><subject>Statistics - Machine Learning</subject><subject>Statistics - Methodology</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNpjYJA0NNAzsTA1NdBPLKrILNMzMjEw1zMwNrYw5mTwdM7PK8nMK80vLVbwLyjJzM2sSizJzM9TSMsvUvBPS8vJzEtVcM5IzEtPVQjIz8wrUXBJLUlNBitJzEtRcC0G6gHr4GFgTUvMKU7lhdLcDPJuriHOHrpgS-MLioDqiirjQZbHgy03JqwCAGIoOl4</recordid><startdate>20240702</startdate><enddate>20240702</enddate><creator>Reimann, Hans</creator><creator>Moka, Sarat</creator><creator>Sofronov, Georgy</creator><scope>EPD</scope><scope>GOX</scope></search><sort><creationdate>20240702</creationdate><title>Continuous Optimization for Offline Change Point Detection and Estimation</title><author>Reimann, Hans ; Moka, Sarat ; Sofronov, Georgy</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-arxiv_primary_2407_033833</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Statistics - Computation</topic><topic>Statistics - Machine Learning</topic><topic>Statistics - Methodology</topic><toplevel>online_resources</toplevel><creatorcontrib>Reimann, Hans</creatorcontrib><creatorcontrib>Moka, Sarat</creatorcontrib><creatorcontrib>Sofronov, Georgy</creatorcontrib><collection>arXiv Statistics</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Reimann, Hans</au><au>Moka, Sarat</au><au>Sofronov, Georgy</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Continuous Optimization for Offline Change Point Detection and Estimation</atitle><date>2024-07-02</date><risdate>2024</risdate><abstract>This work explores use of novel advances in best subset selection for regression modelling via continuous optimization for offline change point detection and estimation in univariate Gaussian data sequences. The approach exploits reformulating the normal mean multiple change point model into a regularized statistical inverse problem enforcing sparsity. After introducing the problem statement, criteria and previous investigations via Lasso-regularization, the recently developed framework of continuous optimization for best subset selection (COMBSS) is briefly introduced and related to the problem at hand. Supervised and unsupervised perspectives are explored with the latter testing different approaches for the choice of regularization penalty parameters via the discrepancy principle and a confidence bound. The main result is an adaptation and evaluation of the COMBSS approach for offline normal mean multiple change-point detection via experimental results on simulated data for different choices of regularisation parameters. Results and future directions are discussed.</abstract><doi>10.48550/arxiv.2407.03383</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2407.03383
ispartof
issn
language eng
recordid cdi_arxiv_primary_2407_03383
source arXiv.org
subjects Statistics - Computation
Statistics - Machine Learning
Statistics - Methodology
title Continuous Optimization for Offline Change Point Detection and Estimation
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-25T14%3A40%3A18IST&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=Continuous%20Optimization%20for%20Offline%20Change%20Point%20Detection%20and%20Estimation&rft.au=Reimann,%20Hans&rft.date=2024-07-02&rft_id=info:doi/10.48550/arxiv.2407.03383&rft_dat=%3Carxiv_GOX%3E2407_03383%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