Neuc-MDS: Non-Euclidean Multidimensional Scaling Through Bilinear Forms

We introduce Non-Euclidean-MDS (Neuc-MDS), an extension of classical Multidimensional Scaling (MDS) that accommodates non-Euclidean and non-metric inputs. The main idea is to generalize the standard inner product to symmetric bilinear forms to utilize the negative eigenvalues of dissimilarity Gram m...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2024-11
Main Authors: Deng, Chengyuan, Gao, Jie, Lu, Kevin, Luo, Feng, Sun, Hongbin, Cheng, Xin
Format: Article
Language:English
Subjects:
Eigenvalues
Error analysis
Error reduction
Lower bounds
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites
container_end_page
container_issue
container_start_page
container_title arXiv.org
container_volume
creator Deng, Chengyuan
Gao, Jie
Lu, Kevin
Luo, Feng
Sun, Hongbin
Cheng, Xin
description We introduce Non-Euclidean-MDS (Neuc-MDS), an extension of classical Multidimensional Scaling (MDS) that accommodates non-Euclidean and non-metric inputs. The main idea is to generalize the standard inner product to symmetric bilinear forms to utilize the negative eigenvalues of dissimilarity Gram matrices. Neuc-MDS efficiently optimizes the choice of (both positive and negative) eigenvalues of the dissimilarity Gram matrix to reduce STRESS, the sum of squared pairwise error. We provide an in-depth error analysis and proofs of the optimality in minimizing lower bounds of STRESS. We demonstrate Neuc-MDS's ability to address limitations of classical MDS raised by prior research, and test it on various synthetic and real-world datasets in comparison with both linear and non-linear dimension reduction methods.
format article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_3130506438</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>3130506438</sourcerecordid><originalsourceid>FETCH-proquest_journals_31305064383</originalsourceid><addsrcrecordid>eNqNjEELgjAYQEcQJOV_GHQezE1NOlZaF73oXYZOncyt9rn_n4d-QKfHg8fboYBxHpEsZuyAQoCZUsrSC0sSHqBnJX1Hykd9xZU1JPedVr0UBpder6pXizSgrBEa153Qyoy4mZz144RvalMpHC6sW-CE9oPQIMMfj-hc5M39Rd7OfryEtZ2td9sHWh5xmtA05hn_r_oCmEs68w</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>3130506438</pqid></control><display><type>article</type><title>Neuc-MDS: Non-Euclidean Multidimensional Scaling Through Bilinear Forms</title><source>ProQuest - Publicly Available Content Database</source><creator>Deng, Chengyuan ; Gao, Jie ; Lu, Kevin ; Luo, Feng ; Sun, Hongbin ; Cheng, Xin</creator><creatorcontrib>Deng, Chengyuan ; Gao, Jie ; Lu, Kevin ; Luo, Feng ; Sun, Hongbin ; Cheng, Xin</creatorcontrib><description>We introduce Non-Euclidean-MDS (Neuc-MDS), an extension of classical Multidimensional Scaling (MDS) that accommodates non-Euclidean and non-metric inputs. The main idea is to generalize the standard inner product to symmetric bilinear forms to utilize the negative eigenvalues of dissimilarity Gram matrices. Neuc-MDS efficiently optimizes the choice of (both positive and negative) eigenvalues of the dissimilarity Gram matrix to reduce STRESS, the sum of squared pairwise error. We provide an in-depth error analysis and proofs of the optimality in minimizing lower bounds of STRESS. We demonstrate Neuc-MDS's ability to address limitations of classical MDS raised by prior research, and test it on various synthetic and real-world datasets in comparison with both linear and non-linear dimension reduction methods.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Eigenvalues ; Error analysis ; Error reduction ; Lower bounds</subject><ispartof>arXiv.org, 2024-11</ispartof><rights>2024. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://www.proquest.com/docview/3130506438?pq-origsite=primo$$EHTML$$P50$$Gproquest$$Hfree_for_read</linktohtml><link.rule.ids>780,784,25753,37012,44590</link.rule.ids></links><search><creatorcontrib>Deng, Chengyuan</creatorcontrib><creatorcontrib>Gao, Jie</creatorcontrib><creatorcontrib>Lu, Kevin</creatorcontrib><creatorcontrib>Luo, Feng</creatorcontrib><creatorcontrib>Sun, Hongbin</creatorcontrib><creatorcontrib>Cheng, Xin</creatorcontrib><title>Neuc-MDS: Non-Euclidean Multidimensional Scaling Through Bilinear Forms</title><title>arXiv.org</title><description>We introduce Non-Euclidean-MDS (Neuc-MDS), an extension of classical Multidimensional Scaling (MDS) that accommodates non-Euclidean and non-metric inputs. The main idea is to generalize the standard inner product to symmetric bilinear forms to utilize the negative eigenvalues of dissimilarity Gram matrices. Neuc-MDS efficiently optimizes the choice of (both positive and negative) eigenvalues of the dissimilarity Gram matrix to reduce STRESS, the sum of squared pairwise error. We provide an in-depth error analysis and proofs of the optimality in minimizing lower bounds of STRESS. We demonstrate Neuc-MDS's ability to address limitations of classical MDS raised by prior research, and test it on various synthetic and real-world datasets in comparison with both linear and non-linear dimension reduction methods.</description><subject>Eigenvalues</subject><subject>Error analysis</subject><subject>Error reduction</subject><subject>Lower bounds</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>PIMPY</sourceid><recordid>eNqNjEELgjAYQEcQJOV_GHQezE1NOlZaF73oXYZOncyt9rn_n4d-QKfHg8fboYBxHpEsZuyAQoCZUsrSC0sSHqBnJX1Hykd9xZU1JPedVr0UBpder6pXizSgrBEa153Qyoy4mZz144RvalMpHC6sW-CE9oPQIMMfj-hc5M39Rd7OfryEtZ2td9sHWh5xmtA05hn_r_oCmEs68w</recordid><startdate>20241116</startdate><enddate>20241116</enddate><creator>Deng, Chengyuan</creator><creator>Gao, Jie</creator><creator>Lu, Kevin</creator><creator>Luo, Feng</creator><creator>Sun, Hongbin</creator><creator>Cheng, Xin</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope></search><sort><creationdate>20241116</creationdate><title>Neuc-MDS: Non-Euclidean Multidimensional Scaling Through Bilinear Forms</title><author>Deng, Chengyuan ; Gao, Jie ; Lu, Kevin ; Luo, Feng ; Sun, Hongbin ; Cheng, Xin</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_31305064383</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Eigenvalues</topic><topic>Error analysis</topic><topic>Error reduction</topic><topic>Lower bounds</topic><toplevel>online_resources</toplevel><creatorcontrib>Deng, Chengyuan</creatorcontrib><creatorcontrib>Gao, Jie</creatorcontrib><creatorcontrib>Lu, Kevin</creatorcontrib><creatorcontrib>Luo, Feng</creatorcontrib><creatorcontrib>Sun, Hongbin</creatorcontrib><creatorcontrib>Cheng, Xin</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science &amp; Engineering Collection</collection><collection>ProQuest Central (Alumni)</collection><collection>ProQuest Central</collection><collection>ProQuest Central Essentials</collection><collection>AUTh Library subscriptions: ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>ProQuest - Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Deng, Chengyuan</au><au>Gao, Jie</au><au>Lu, Kevin</au><au>Luo, Feng</au><au>Sun, Hongbin</au><au>Cheng, Xin</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>Neuc-MDS: Non-Euclidean Multidimensional Scaling Through Bilinear Forms</atitle><jtitle>arXiv.org</jtitle><date>2024-11-16</date><risdate>2024</risdate><eissn>2331-8422</eissn><abstract>We introduce Non-Euclidean-MDS (Neuc-MDS), an extension of classical Multidimensional Scaling (MDS) that accommodates non-Euclidean and non-metric inputs. The main idea is to generalize the standard inner product to symmetric bilinear forms to utilize the negative eigenvalues of dissimilarity Gram matrices. Neuc-MDS efficiently optimizes the choice of (both positive and negative) eigenvalues of the dissimilarity Gram matrix to reduce STRESS, the sum of squared pairwise error. We provide an in-depth error analysis and proofs of the optimality in minimizing lower bounds of STRESS. We demonstrate Neuc-MDS's ability to address limitations of classical MDS raised by prior research, and test it on various synthetic and real-world datasets in comparison with both linear and non-linear dimension reduction methods.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier EISSN: 2331-8422
ispartof arXiv.org, 2024-11
issn 2331-8422
language eng
recordid cdi_proquest_journals_3130506438
source ProQuest - Publicly Available Content Database
subjects Eigenvalues
Error analysis
Error reduction
Lower bounds
title Neuc-MDS: Non-Euclidean Multidimensional Scaling Through Bilinear Forms
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-04T12%3A45%3A01IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=document&rft.atitle=Neuc-MDS:%20Non-Euclidean%20Multidimensional%20Scaling%20Through%20Bilinear%20Forms&rft.jtitle=arXiv.org&rft.au=Deng,%20Chengyuan&rft.date=2024-11-16&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E3130506438%3C/proquest%3E%3Cgrp_id%3Ecdi_FETCH-proquest_journals_31305064383%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=3130506438&rft_id=info:pmid/&rfr_iscdi=true