Multi-Layer Kernel Machines: Fast and Optimal Nonparametric Regression with Uncertainty Quantification

Kernel ridge regression (KRR) is widely used for nonparametric regression over reproducing kernel Hilbert spaces. It offers powerful modeling capabilities at the cost of significant computational costs, which typically require $O(n^3)$ computational time and $O(n^2)$ storage space, with the sample s...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Dai, Xiaowu, Zhong, Huiying
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 Dai, Xiaowu
Zhong, Huiying
description Kernel ridge regression (KRR) is widely used for nonparametric regression over reproducing kernel Hilbert spaces. It offers powerful modeling capabilities at the cost of significant computational costs, which typically require $O(n^3)$ computational time and $O(n^2)$ storage space, with the sample size n. We introduce a novel framework of multi-layer kernel machines that approximate KRR by employing a multi-layer structure and random features, and study how the optimal number of random features and layer sizes can be chosen while still preserving the minimax optimality of the approximate KRR estimate. For various classes of random features, including those corresponding to Gaussian and Matern kernels, we prove that multi-layer kernel machines can achieve $O(n^2\log^2n)$ computational time and $O(n\log^2n)$ storage space, and yield fast and minimax optimal approximations to the KRR estimate for nonparametric regression. Moreover, we construct uncertainty quantification for multi-layer kernel machines by using conformal prediction techniques with robust coverage properties. The analysis and theoretical predictions are supported by simulations and real data examples.
doi_str_mv 10.48550/arxiv.2403.09907
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2403_09907</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2403_09907</sourcerecordid><originalsourceid>FETCH-LOGICAL-a677-c372a5a88a9284a85fb20be7743a160581035a6a92e5c3e5a9e41409cf0f9b1d3</originalsourceid><addsrcrecordid>eNotj7FOwzAURb0woMIHMNU_kODEdmyzoYoCIqUqKnP04j5TS6kbOS6QvycUpjsc6eocQm4KlgstJbuF-O0_81IwnjNjmLokbnXqks9qGDHSF4wBO7oCu_cBhzu6hCFRCDu67pM_QEdfj6GHCAdM0Vv6hh8Rh8EfA_3yaU_fg8WYwIc00s0JQvLOW0gTvyIXDroBr_93RrbLh-3iKavXj8-L-zqDSqnMclWCBK3BlFqAlq4tWYtKCQ5FxaQuGJdQTRSl5SjBoCgEM9YxZ9pix2dk_nd7Dm36OEnHsfkNbs7B_Ac7SVHj</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Multi-Layer Kernel Machines: Fast and Optimal Nonparametric Regression with Uncertainty Quantification</title><source>arXiv.org</source><creator>Dai, Xiaowu ; Zhong, Huiying</creator><creatorcontrib>Dai, Xiaowu ; Zhong, Huiying</creatorcontrib><description>Kernel ridge regression (KRR) is widely used for nonparametric regression over reproducing kernel Hilbert spaces. It offers powerful modeling capabilities at the cost of significant computational costs, which typically require $O(n^3)$ computational time and $O(n^2)$ storage space, with the sample size n. We introduce a novel framework of multi-layer kernel machines that approximate KRR by employing a multi-layer structure and random features, and study how the optimal number of random features and layer sizes can be chosen while still preserving the minimax optimality of the approximate KRR estimate. For various classes of random features, including those corresponding to Gaussian and Matern kernels, we prove that multi-layer kernel machines can achieve $O(n^2\log^2n)$ computational time and $O(n\log^2n)$ storage space, and yield fast and minimax optimal approximations to the KRR estimate for nonparametric regression. Moreover, we construct uncertainty quantification for multi-layer kernel machines by using conformal prediction techniques with robust coverage properties. The analysis and theoretical predictions are supported by simulations and real data examples.</description><identifier>DOI: 10.48550/arxiv.2403.09907</identifier><language>eng</language><subject>Statistics - Methodology</subject><creationdate>2024-03</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/2403.09907$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2403.09907$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Dai, Xiaowu</creatorcontrib><creatorcontrib>Zhong, Huiying</creatorcontrib><title>Multi-Layer Kernel Machines: Fast and Optimal Nonparametric Regression with Uncertainty Quantification</title><description>Kernel ridge regression (KRR) is widely used for nonparametric regression over reproducing kernel Hilbert spaces. It offers powerful modeling capabilities at the cost of significant computational costs, which typically require $O(n^3)$ computational time and $O(n^2)$ storage space, with the sample size n. We introduce a novel framework of multi-layer kernel machines that approximate KRR by employing a multi-layer structure and random features, and study how the optimal number of random features and layer sizes can be chosen while still preserving the minimax optimality of the approximate KRR estimate. For various classes of random features, including those corresponding to Gaussian and Matern kernels, we prove that multi-layer kernel machines can achieve $O(n^2\log^2n)$ computational time and $O(n\log^2n)$ storage space, and yield fast and minimax optimal approximations to the KRR estimate for nonparametric regression. Moreover, we construct uncertainty quantification for multi-layer kernel machines by using conformal prediction techniques with robust coverage properties. The analysis and theoretical predictions are supported by simulations and real data examples.</description><subject>Statistics - Methodology</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotj7FOwzAURb0woMIHMNU_kODEdmyzoYoCIqUqKnP04j5TS6kbOS6QvycUpjsc6eocQm4KlgstJbuF-O0_81IwnjNjmLokbnXqks9qGDHSF4wBO7oCu_cBhzu6hCFRCDu67pM_QEdfj6GHCAdM0Vv6hh8Rh8EfA_3yaU_fg8WYwIc00s0JQvLOW0gTvyIXDroBr_93RrbLh-3iKavXj8-L-zqDSqnMclWCBK3BlFqAlq4tWYtKCQ5FxaQuGJdQTRSl5SjBoCgEM9YxZ9pix2dk_nd7Dm36OEnHsfkNbs7B_Ac7SVHj</recordid><startdate>20240314</startdate><enddate>20240314</enddate><creator>Dai, Xiaowu</creator><creator>Zhong, Huiying</creator><scope>EPD</scope><scope>GOX</scope></search><sort><creationdate>20240314</creationdate><title>Multi-Layer Kernel Machines: Fast and Optimal Nonparametric Regression with Uncertainty Quantification</title><author>Dai, Xiaowu ; Zhong, Huiying</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a677-c372a5a88a9284a85fb20be7743a160581035a6a92e5c3e5a9e41409cf0f9b1d3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Statistics - Methodology</topic><toplevel>online_resources</toplevel><creatorcontrib>Dai, Xiaowu</creatorcontrib><creatorcontrib>Zhong, Huiying</creatorcontrib><collection>arXiv Statistics</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Dai, Xiaowu</au><au>Zhong, Huiying</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Multi-Layer Kernel Machines: Fast and Optimal Nonparametric Regression with Uncertainty Quantification</atitle><date>2024-03-14</date><risdate>2024</risdate><abstract>Kernel ridge regression (KRR) is widely used for nonparametric regression over reproducing kernel Hilbert spaces. It offers powerful modeling capabilities at the cost of significant computational costs, which typically require $O(n^3)$ computational time and $O(n^2)$ storage space, with the sample size n. We introduce a novel framework of multi-layer kernel machines that approximate KRR by employing a multi-layer structure and random features, and study how the optimal number of random features and layer sizes can be chosen while still preserving the minimax optimality of the approximate KRR estimate. For various classes of random features, including those corresponding to Gaussian and Matern kernels, we prove that multi-layer kernel machines can achieve $O(n^2\log^2n)$ computational time and $O(n\log^2n)$ storage space, and yield fast and minimax optimal approximations to the KRR estimate for nonparametric regression. Moreover, we construct uncertainty quantification for multi-layer kernel machines by using conformal prediction techniques with robust coverage properties. The analysis and theoretical predictions are supported by simulations and real data examples.</abstract><doi>10.48550/arxiv.2403.09907</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2403.09907
ispartof
issn
language eng
recordid cdi_arxiv_primary_2403_09907
source arXiv.org
subjects Statistics - Methodology
title Multi-Layer Kernel Machines: Fast and Optimal Nonparametric Regression with Uncertainty Quantification
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-02T23%3A44%3A14IST&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=Multi-Layer%20Kernel%20Machines:%20Fast%20and%20Optimal%20Nonparametric%20Regression%20with%20Uncertainty%20Quantification&rft.au=Dai,%20Xiaowu&rft.date=2024-03-14&rft_id=info:doi/10.48550/arxiv.2403.09907&rft_dat=%3Carxiv_GOX%3E2403_09907%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