Streaming Kernel PCA with \(\tilde{O}(\sqrt{n})\) Random Features

We study the statistical and computational aspects of kernel principal component analysis using random Fourier features and show that under mild assumptions, \(O(\sqrt{n} \log n)\) features suffices to achieve \(O(1/\epsilon^2)\) sample complexity. Furthermore, we give a memory efficient streaming a...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2018-11
Main Authors: Ullah, Enayat, Mianjy, Poorya, Marinov, Teodor V, Arora, Raman
Format: Article
Language:English
Subjects:
Algorithms
Kernels
Principal components analysis
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 Ullah, Enayat
Mianjy, Poorya
Marinov, Teodor V
Arora, Raman
description We study the statistical and computational aspects of kernel principal component analysis using random Fourier features and show that under mild assumptions, \(O(\sqrt{n} \log n)\) features suffices to achieve \(O(1/\epsilon^2)\) sample complexity. Furthermore, we give a memory efficient streaming algorithm based on classical Oja's algorithm that achieves this rate.
format article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2092756860</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2092756860</sourcerecordid><originalsourceid>FETCH-proquest_journals_20927568603</originalsourceid><addsrcrecordid>eNpjYuA0MjY21LUwMTLiYOAtLs4yMDAwMjM3MjU15mRwDC4pSk3MzcxLV_BOLcpLzVEIcHZUKM8syVCI0YgpycxJSa32r9WIKS4sKqnOq9WM0VQISsxLyc9VcEtNLCktSi3mYWBNS8wpTuWF0twMym6uIc4eugVF-YWlqcUl8Vn5pUV5QKl4IwNLI3NTMwszA2PiVAEAGPk4tg</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2092756860</pqid></control><display><type>article</type><title>Streaming Kernel PCA with \(\tilde{O}(\sqrt{n})\) Random Features</title><source>Publicly Available Content Database</source><creator>Ullah, Enayat ; Mianjy, Poorya ; Marinov, Teodor V ; Arora, Raman</creator><creatorcontrib>Ullah, Enayat ; Mianjy, Poorya ; Marinov, Teodor V ; Arora, Raman</creatorcontrib><description>We study the statistical and computational aspects of kernel principal component analysis using random Fourier features and show that under mild assumptions, \(O(\sqrt{n} \log n)\) features suffices to achieve \(O(1/\epsilon^2)\) sample complexity. Furthermore, we give a memory efficient streaming algorithm based on classical Oja's algorithm that achieves this rate.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Algorithms ; Kernels ; Principal components analysis</subject><ispartof>arXiv.org, 2018-11</ispartof><rights>2018. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (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/2092756860?pq-origsite=primo$$EHTML$$P50$$Gproquest$$Hfree_for_read</linktohtml><link.rule.ids>777,781,25734,36993,44571</link.rule.ids></links><search><creatorcontrib>Ullah, Enayat</creatorcontrib><creatorcontrib>Mianjy, Poorya</creatorcontrib><creatorcontrib>Marinov, Teodor V</creatorcontrib><creatorcontrib>Arora, Raman</creatorcontrib><title>Streaming Kernel PCA with \(\tilde{O}(\sqrt{n})\) Random Features</title><title>arXiv.org</title><description>We study the statistical and computational aspects of kernel principal component analysis using random Fourier features and show that under mild assumptions, \(O(\sqrt{n} \log n)\) features suffices to achieve \(O(1/\epsilon^2)\) sample complexity. Furthermore, we give a memory efficient streaming algorithm based on classical Oja's algorithm that achieves this rate.</description><subject>Algorithms</subject><subject>Kernels</subject><subject>Principal components analysis</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2018</creationdate><recordtype>article</recordtype><sourceid>PIMPY</sourceid><recordid>eNpjYuA0MjY21LUwMTLiYOAtLs4yMDAwMjM3MjU15mRwDC4pSk3MzcxLV_BOLcpLzVEIcHZUKM8syVCI0YgpycxJSa32r9WIKS4sKqnOq9WM0VQISsxLyc9VcEtNLCktSi3mYWBNS8wpTuWF0twMym6uIc4eugVF-YWlqcUl8Vn5pUV5QKl4IwNLI3NTMwszA2PiVAEAGPk4tg</recordid><startdate>20181115</startdate><enddate>20181115</enddate><creator>Ullah, Enayat</creator><creator>Mianjy, Poorya</creator><creator>Marinov, Teodor V</creator><creator>Arora, Raman</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>20181115</creationdate><title>Streaming Kernel PCA with \(\tilde{O}(\sqrt{n})\) Random Features</title><author>Ullah, Enayat ; Mianjy, Poorya ; Marinov, Teodor V ; Arora, Raman</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_20927568603</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2018</creationdate><topic>Algorithms</topic><topic>Kernels</topic><topic>Principal components analysis</topic><toplevel>online_resources</toplevel><creatorcontrib>Ullah, Enayat</creatorcontrib><creatorcontrib>Mianjy, Poorya</creatorcontrib><creatorcontrib>Marinov, Teodor V</creatorcontrib><creatorcontrib>Arora, Raman</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>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>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>Ullah, Enayat</au><au>Mianjy, Poorya</au><au>Marinov, Teodor V</au><au>Arora, Raman</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>Streaming Kernel PCA with \(\tilde{O}(\sqrt{n})\) Random Features</atitle><jtitle>arXiv.org</jtitle><date>2018-11-15</date><risdate>2018</risdate><eissn>2331-8422</eissn><abstract>We study the statistical and computational aspects of kernel principal component analysis using random Fourier features and show that under mild assumptions, \(O(\sqrt{n} \log n)\) features suffices to achieve \(O(1/\epsilon^2)\) sample complexity. Furthermore, we give a memory efficient streaming algorithm based on classical Oja's algorithm that achieves this rate.</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, 2018-11
issn 2331-8422
language eng
recordid cdi_proquest_journals_2092756860
source Publicly Available Content Database
subjects Algorithms
Kernels
Principal components analysis
title Streaming Kernel PCA with \(\tilde{O}(\sqrt{n})\) Random Features
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-19T20%3A40%3A49IST&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=Streaming%20Kernel%20PCA%20with%20%5C(%5Ctilde%7BO%7D(%5Csqrt%7Bn%7D)%5C)%20Random%20Features&rft.jtitle=arXiv.org&rft.au=Ullah,%20Enayat&rft.date=2018-11-15&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2092756860%3C/proquest%3E%3Cgrp_id%3Ecdi_FETCH-proquest_journals_20927568603%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=2092756860&rft_id=info:pmid/&rfr_iscdi=true