Nonparametric Regression in Dirichlet Spaces: A Random Obstacle Approach

In this paper, we consider nonparametric estimation over general Dirichlet metric measure spaces. Unlike the more commonly studied reproducing kernel Hilbert space, whose elements may be defined pointwise, a Dirichlet space typically only contain equivalence classes, i.e. its elements are only uniqu...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Talwai, Prem, Simchi-Levi, David
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 Talwai, Prem
Simchi-Levi, David
description In this paper, we consider nonparametric estimation over general Dirichlet metric measure spaces. Unlike the more commonly studied reproducing kernel Hilbert space, whose elements may be defined pointwise, a Dirichlet space typically only contain equivalence classes, i.e. its elements are only unique almost everywhere. This lack of pointwise definition presents significant challenges in the context of nonparametric estimation, for example the classical ridge regression problem is ill-posed. In this paper, we develop a new technique for renormalizing the ridge loss by replacing pointwise evaluations with certain \textit{local means} around the boundaries of obstacles centered at each data point. The resulting renormalized empirical risk functional is well-posed and even admits a representer theorem in terms of certain equilibrium potentials, which are truncated versions of the associated Green function, cut-off at a data-driven threshold. We study the global, out-of-sample consistency of the sample minimizer, and derive an adaptive upper bound on its convergence rate that highlights the interplay of the analytic, geometric, and probabilistic properties of the Dirichlet form. We also construct a simple regressogram type estimator that achieves the minimax optimal estimation rate over certain $L^p$ subsets of a Dirichlet ball with some knowledge of the geometry of the metric measure space. Our framework notably does not require the smoothness of the underlying space, and is applicable to both manifold and fractal settings. To the best of our knowledge, this is the first paper to obtain out-of-sample convergence guarantees in the framework of general metric measure Dirichlet spaces.
doi_str_mv 10.48550/arxiv.2412.14357
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2412_14357</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2412_14357</sourcerecordid><originalsourceid>FETCH-arxiv_primary_2412_143573</originalsourceid><addsrcrecordid>eNpjYJA0NNAzsTA1NdBPLKrILNMzMjE00jM0MTY152Tw8MvPK0gsSsxNLSnKTFYISk0vSi0uzszPU8jMU3DJBIpl5KSWKAQXJCanFlspOCoEJeal5Ocq-CcVlyQm56QqOBYUFOUnJmfwMLCmJeYUp_JCaW4GeTfXEGcPXbCd8QVFmbmJRZXxILvjwXYbE1YBANN5OUw</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Nonparametric Regression in Dirichlet Spaces: A Random Obstacle Approach</title><source>arXiv.org</source><creator>Talwai, Prem ; Simchi-Levi, David</creator><creatorcontrib>Talwai, Prem ; Simchi-Levi, David</creatorcontrib><description>In this paper, we consider nonparametric estimation over general Dirichlet metric measure spaces. Unlike the more commonly studied reproducing kernel Hilbert space, whose elements may be defined pointwise, a Dirichlet space typically only contain equivalence classes, i.e. its elements are only unique almost everywhere. This lack of pointwise definition presents significant challenges in the context of nonparametric estimation, for example the classical ridge regression problem is ill-posed. In this paper, we develop a new technique for renormalizing the ridge loss by replacing pointwise evaluations with certain \textit{local means} around the boundaries of obstacles centered at each data point. The resulting renormalized empirical risk functional is well-posed and even admits a representer theorem in terms of certain equilibrium potentials, which are truncated versions of the associated Green function, cut-off at a data-driven threshold. We study the global, out-of-sample consistency of the sample minimizer, and derive an adaptive upper bound on its convergence rate that highlights the interplay of the analytic, geometric, and probabilistic properties of the Dirichlet form. We also construct a simple regressogram type estimator that achieves the minimax optimal estimation rate over certain $L^p$ subsets of a Dirichlet ball with some knowledge of the geometry of the metric measure space. Our framework notably does not require the smoothness of the underlying space, and is applicable to both manifold and fractal settings. To the best of our knowledge, this is the first paper to obtain out-of-sample convergence guarantees in the framework of general metric measure Dirichlet spaces.</description><identifier>DOI: 10.48550/arxiv.2412.14357</identifier><language>eng</language><subject>Mathematics - Statistics Theory ; Statistics - Theory</subject><creationdate>2024-12</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/2412.14357$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2412.14357$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Talwai, Prem</creatorcontrib><creatorcontrib>Simchi-Levi, David</creatorcontrib><title>Nonparametric Regression in Dirichlet Spaces: A Random Obstacle Approach</title><description>In this paper, we consider nonparametric estimation over general Dirichlet metric measure spaces. Unlike the more commonly studied reproducing kernel Hilbert space, whose elements may be defined pointwise, a Dirichlet space typically only contain equivalence classes, i.e. its elements are only unique almost everywhere. This lack of pointwise definition presents significant challenges in the context of nonparametric estimation, for example the classical ridge regression problem is ill-posed. In this paper, we develop a new technique for renormalizing the ridge loss by replacing pointwise evaluations with certain \textit{local means} around the boundaries of obstacles centered at each data point. The resulting renormalized empirical risk functional is well-posed and even admits a representer theorem in terms of certain equilibrium potentials, which are truncated versions of the associated Green function, cut-off at a data-driven threshold. We study the global, out-of-sample consistency of the sample minimizer, and derive an adaptive upper bound on its convergence rate that highlights the interplay of the analytic, geometric, and probabilistic properties of the Dirichlet form. We also construct a simple regressogram type estimator that achieves the minimax optimal estimation rate over certain $L^p$ subsets of a Dirichlet ball with some knowledge of the geometry of the metric measure space. Our framework notably does not require the smoothness of the underlying space, and is applicable to both manifold and fractal settings. To the best of our knowledge, this is the first paper to obtain out-of-sample convergence guarantees in the framework of general metric measure Dirichlet spaces.</description><subject>Mathematics - Statistics Theory</subject><subject>Statistics - Theory</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNpjYJA0NNAzsTA1NdBPLKrILNMzMjE00jM0MTY152Tw8MvPK0gsSsxNLSnKTFYISk0vSi0uzszPU8jMU3DJBIpl5KSWKAQXJCanFlspOCoEJeal5Ocq-CcVlyQm56QqOBYUFOUnJmfwMLCmJeYUp_JCaW4GeTfXEGcPXbCd8QVFmbmJRZXxILvjwXYbE1YBANN5OUw</recordid><startdate>20241218</startdate><enddate>20241218</enddate><creator>Talwai, Prem</creator><creator>Simchi-Levi, David</creator><scope>AKZ</scope><scope>EPD</scope><scope>GOX</scope></search><sort><creationdate>20241218</creationdate><title>Nonparametric Regression in Dirichlet Spaces: A Random Obstacle Approach</title><author>Talwai, Prem ; Simchi-Levi, David</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-arxiv_primary_2412_143573</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Mathematics - Statistics Theory</topic><topic>Statistics - Theory</topic><toplevel>online_resources</toplevel><creatorcontrib>Talwai, Prem</creatorcontrib><creatorcontrib>Simchi-Levi, David</creatorcontrib><collection>arXiv Mathematics</collection><collection>arXiv Statistics</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Talwai, Prem</au><au>Simchi-Levi, David</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Nonparametric Regression in Dirichlet Spaces: A Random Obstacle Approach</atitle><date>2024-12-18</date><risdate>2024</risdate><abstract>In this paper, we consider nonparametric estimation over general Dirichlet metric measure spaces. Unlike the more commonly studied reproducing kernel Hilbert space, whose elements may be defined pointwise, a Dirichlet space typically only contain equivalence classes, i.e. its elements are only unique almost everywhere. This lack of pointwise definition presents significant challenges in the context of nonparametric estimation, for example the classical ridge regression problem is ill-posed. In this paper, we develop a new technique for renormalizing the ridge loss by replacing pointwise evaluations with certain \textit{local means} around the boundaries of obstacles centered at each data point. The resulting renormalized empirical risk functional is well-posed and even admits a representer theorem in terms of certain equilibrium potentials, which are truncated versions of the associated Green function, cut-off at a data-driven threshold. We study the global, out-of-sample consistency of the sample minimizer, and derive an adaptive upper bound on its convergence rate that highlights the interplay of the analytic, geometric, and probabilistic properties of the Dirichlet form. We also construct a simple regressogram type estimator that achieves the minimax optimal estimation rate over certain $L^p$ subsets of a Dirichlet ball with some knowledge of the geometry of the metric measure space. Our framework notably does not require the smoothness of the underlying space, and is applicable to both manifold and fractal settings. To the best of our knowledge, this is the first paper to obtain out-of-sample convergence guarantees in the framework of general metric measure Dirichlet spaces.</abstract><doi>10.48550/arxiv.2412.14357</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2412.14357
ispartof
issn
language eng
recordid cdi_arxiv_primary_2412_14357
source arXiv.org
subjects Mathematics - Statistics Theory
Statistics - Theory
title Nonparametric Regression in Dirichlet Spaces: A Random Obstacle Approach
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-28T01%3A29%3A10IST&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=Nonparametric%20Regression%20in%20Dirichlet%20Spaces:%20A%20Random%20Obstacle%20Approach&rft.au=Talwai,%20Prem&rft.date=2024-12-18&rft_id=info:doi/10.48550/arxiv.2412.14357&rft_dat=%3Carxiv_GOX%3E2412_14357%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