{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T00:36:41Z","timestamp":1783643801511,"version":"3.55.0"},"reference-count":42,"publisher":"Oxford University Press (OUP)","issue":"5","license":[{"start":{"date-parts":[[2024,5,22]],"date-time":"2024-05-22T00:00:00Z","timestamp":1716336000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/pages\/standard-publication-reuse-rights"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key R&D Program of China","doi-asserted-by":"publisher","award":["2023YFA1008700 and 2023YFA1008703"],"award-info":[{"award-number":["2023YFA1008700 and 2023YFA1008703"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["12371289"],"award-info":[{"award-number":["12371289"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shanghai Pilot Program for Basic Research","award":["TQ20220105"],"award-info":[{"award-number":["TQ20220105"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,11,13]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Neural networks and random forests are popular and promising tools for machine learning. This article explores the proper integration of these two approaches for nonparametric regression to improve the performance of a single approach. Specifically, we propose a neural network estimator with local enhancement provided by random forests. It naturally synthesizes the local relation adaptivity of random forests and the strong global approximation ability of neural networks. Based on the classical empirical risk minimization framework, we establish a nonasymptotic error bound for the estimator. By utilizing advanced U-process theory and an appropriate network structure, we can further improve the convergence rate to the nearly minimax rate. Also with the assistance of random forests, we can implement gradient learning with neural networks. Comprehensive simulation studies and real data applications demonstrate the superiority of our proposal.<\/jats:p>","DOI":"10.1093\/jrsssb\/qkae038","type":"journal-article","created":{"date-parts":[[2024,5,22]],"date-time":"2024-05-22T14:15:29Z","timestamp":1716387329000},"page":"1435-1454","source":"Crossref","is-referenced-by-count":11,"title":["Neural networks meet random forests"],"prefix":"10.1093","volume":"86","author":[{"given":"Rui","family":"Qiu","sequence":"first","affiliation":[{"name":"School of Statistics, KLATASDS-MOE, East China Normal University , Shanghai 200062 ,","place":["People\u2019s Republic of China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuntuo","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Statistics, KLATASDS-MOE, East China Normal University , Shanghai 200062 ,","place":["People\u2019s Republic of China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1711-3971","authenticated-orcid":false,"given":"Zhou","family":"Yu","sequence":"additional","affiliation":[{"name":"School of Statistics, KLATASDS-MOE, East China Normal University , Shanghai 200062 ,","place":["People\u2019s Republic of China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2024,5,22]]},"reference":[{"key":"2024111314110490500_qkae038-B1","author":"Arnould","year":"2021"},{"issue":"4","key":"2024111314110490500_qkae038-B2","doi-asserted-by":"publisher","first-page":"1497","DOI":"10.1214\/009053605000000282","article-title":"Local Rademacher complexities","volume":"33","author":"Bartlett","year":"2005","journal-title":"Annals of Statistics"},{"issue":"63","key":"2024111314110490500_qkae038-B3","first-page":"1","article-title":"Nearly-tight VC-dimension and pseudodimension bounds for piecewise linear neural networks","volume":"20","author":"Bartlett","year":"2019","journal-title":"Journal of Machine Learning Research"},{"issue":"4","key":"2024111314110490500_qkae038-B4","doi-asserted-by":"publisher","first-page":"2261","DOI":"10.1214\/18-AOS1747","article-title":"On deep learning as a remedy for the curse of dimensionality in nonparametric regression","volume":"47","author":"Bauer","year":"2019","journal-title":"Annals of Statistics"},{"issue":"1","key":"2024111314110490500_qkae038-B5","doi-asserted-by":"publisher","first-page":"1063","DOI":"10.48550\/arXiv.1005.0208","article-title":"Analysis of a random forests model","volume":"13","author":"Biau","year":"2012","journal-title":"Journal of Machine Learning Research"},{"issue":"9","key":"2024111314110490500_qkae038-B6","doi-asserted-by":"publisher","first-page":"2015","DOI":"10.5555\/1390681.1442799","article-title":"Consistency of random forests and other averaging classifiers","volume":"9","author":"Biau","year":"2008","journal-title":"Journal of Machine Learning Research"},{"issue":"2","key":"2024111314110490500_qkae038-B7","doi-asserted-by":"publisher","first-page":"347","DOI":"10.1007\/s13171-018-0133-y","article-title":"Neural random forests","volume":"81","author":"Biau","year":"2019","journal-title":"Sankhya A"},{"issue":"1","key":"2024111314110490500_qkae038-B8","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Machine Learning"},{"issue":"4","key":"2024111314110490500_qkae038-B9","doi-asserted-by":"publisher","first-page":"1203","DOI":"10.1093\/imaiai\/iaac001","article-title":"Nonparametric regression on low-dimensional manifolds using deep ReLU networks: Function approximation and statistical recovery","volume":"11","author":"Chen","year":"2022","journal-title":"Information and Inference: A Journal of the IMA"},{"issue":"6","key":"2024111314110490500_qkae038-B10","doi-asserted-by":"publisher","first-page":"323","DOI":"10.1016\/j.ygeno.2012.04.003","article-title":"Random forests for genomic data analysis","volume":"99","author":"Chen","year":"2012","journal-title":"Genomics"},{"issue":"504","key":"2024111314110490500_qkae038-B11","doi-asserted-by":"publisher","first-page":"1421","DOI":"10.1080\/01621459.2013.827984","article-title":"Local linear regression on manifolds and its geometric interpretation","volume":"108","author":"Cheng","year":"2013","journal-title":"Journal of the American Statistical Association"},{"issue":"6","key":"2024111314110490500_qkae038-B12","doi-asserted-by":"publisher","first-page":"3415","DOI":"10.1214\/22-AOS2234","article-title":"Asymptotic properties of high-dimensional random forests","volume":"50","author":"Chi","year":"2022","journal-title":"Annals of Statistics"},{"key":"2024111314110490500_qkae038-B13","author":"Denil","year":"2014"},{"key":"2024111314110490500_qkae038-B14","doi-asserted-by":"crossref","DOI":"10.1201\/9780203748725","volume-title":"Local polynomial modelling and its applications","author":"Fan","year":"2018"},{"issue":"1","key":"2024111314110490500_qkae038-B15","doi-asserted-by":"publisher","first-page":"181","DOI":"10.3982\/ECTA16901","article-title":"Deep neural networks for estimation and inference","volume":"89","author":"Farrell","year":"2021","journal-title":"Econometrica"},{"issue":"2","key":"2024111314110490500_qkae038-B16","doi-asserted-by":"publisher","first-page":"503","DOI":"10.1080\/10618600.2020.1831930","article-title":"Local linear forests","volume":"30","author":"Friedberg","year":"2020","journal-title":"Journal of Computational and Graphical Statistics"},{"key":"2024111314110490500_qkae038-B17","author":"Gao","year":"2020"},{"issue":"5786","key":"2024111314110490500_qkae038-B18","doi-asserted-by":"publisher","first-page":"504","DOI":"10.1126\/science.1127647","article-title":"Reducing the dimensionality of data with neural networks","volume":"313","author":"Hinton","year":"2006","journal-title":"Science"},{"issue":"3","key":"2024111314110490500_qkae038-B19","doi-asserted-by":"publisher","first-page":"293","DOI":"10.1214\/aoms\/1177730196","article-title":"A class of statistics with asymptotically normal distribution","volume":"19","author":"Hoeffding","year":"1948","journal-title":"Annals of Mathematical Statistics"},{"issue":"2","key":"2024111314110490500_qkae038-B20","doi-asserted-by":"publisher","first-page":"691","DOI":"10.1214\/23-AOS2266","article-title":"Deep nonparametric regression on approximate manifolds: Nonasymptotic error bounds with polynomial prefactors","volume":"51","author":"Jiao","year":"2023","journal-title":"Annals of Statistics"},{"key":"2024111314110490500_qkae038-B22","author":"Klusowski","year":"2021"},{"issue":"545","key":"2024111314110490500_qkae038-B23","doi-asserted-by":"publisher","first-page":"525","DOI":"10.1080\/01621459.2022.2126782","article-title":"Large scale prediction with decision trees","volume":"119","author":"Klusowski","year":"2024","journal-title":"Journal of the American Statistical Association"},{"issue":"6","key":"2024111314110490500_qkae038-B24","doi-asserted-by":"publisher","first-page":"4032","DOI":"10.1109\/TIT.2022.3146620","article-title":"Estimation of a function of low local dimensionality by deep neural networks","volume":"68","author":"Kohler","year":"2019","journal-title":"IEEE Transactions on Information Theory"},{"key":"2024111314110490500_qkae038-B25","author":"Kontschieder","year":"2015"},{"key":"2024111314110490500_qkae038-B26","author":"Lakshminarayanan","year":"2014"},{"issue":"474","key":"2024111314110490500_qkae038-B27","doi-asserted-by":"publisher","first-page":"578","DOI":"10.1198\/016214505000001230","article-title":"Random forests and adaptive nearest neighbors","volume":"101","author":"Lin","year":"2006","journal-title":"Journal of the American Statistical Association"},{"issue":"1","key":"2024111314110490500_qkae038-B28","doi-asserted-by":"publisher","first-page":"841","DOI":"10.48550\/arXiv.1404.6473","article-title":"Quantifying uncertainty in random forests via confidence intervals and hypothesis tests","volume":"17","author":"Mentch","year":"2016","journal-title":"Journal of Machine Learning Research"},{"issue":"1","key":"2024111314110490500_qkae038-B29","doi-asserted-by":"publisher","first-page":"6918","DOI":"10.48550\/arXiv.1911.00190","article-title":"Randomization as regularization: A degrees of freedom explanation for random forest success","volume":"21","author":"Mentch","year":"2020","journal-title":"Journal of Machine Learning Research"},{"issue":"4","key":"2024111314110490500_qkae038-B30","doi-asserted-by":"publisher","first-page":"2253","DOI":"10.1214\/19-AOS1886","article-title":"Minimax optimal rates for Mondrian trees and forests","volume":"48","author":"Mourtada","year":"2020","journal-title":"Annals of Statistics"},{"issue":"1","key":"2024111314110490500_qkae038-B31","doi-asserted-by":"publisher","first-page":"232","DOI":"10.1214\/21-EJS1958","article-title":"Rates of convergence for random forests via generalized U-statistics","volume":"16","author":"Peng","year":"2022","journal-title":"Electronic Journal of Statistics"},{"issue":"4","key":"2024111314110490500_qkae038-B32","doi-asserted-by":"publisher","first-page":"1875","DOI":"10.1214\/24-aos2351","article-title":"Nonparametric regression using deep neural networks with ReLU activation function","volume":"48","author":"Schmidt-Hieber","year":"2020","journal-title":"Annals of Statistics"},{"issue":"3","key":"2024111314110490500_qkae038-B33","doi-asserted-by":"publisher","first-page":"1485","DOI":"10.1109\/TIT.2016.2514489","article-title":"Random forests and kernel methods","volume":"62","author":"Scornet","year":"2016","journal-title":"IEEE Transactions on Information Theory"},{"issue":"4","key":"2024111314110490500_qkae038-B34","doi-asserted-by":"publisher","first-page":"1716","DOI":"10.1214\/15-AOS1321","article-title":"Consistency of random forests","volume":"43","author":"Scornet","year":"2015","journal-title":"Annals of Statistics"},{"key":"2024111314110490500_qkae038-B35","doi-asserted-by":"publisher","first-page":"74","DOI":"10.1016\/j.neunet.2019.07.011","article-title":"Nonlinear approximation via compositions","volume":"119","author":"Shen","year":"2019","journal-title":"Neural Networks"},{"issue":"5","key":"2024111314110490500_qkae038-B36","doi-asserted-by":"publisher","first-page":"1768","DOI":"10.4208\/cicp","article-title":"Deep network approximation characterized by number of neurons","volume":"28","author":"Shen","year":"2020","journal-title":"Communications in Computational Physics"},{"key":"2024111314110490500_qkae038-B37","doi-asserted-by":"publisher","first-page":"101","DOI":"10.1016\/j.matpur.2021.07.009","article-title":"Optimal approximation rate of ReLU networks in terms of width and depth","volume":"157","author":"Shen","year":"2022","journal-title":"Journal de Math\u00e9matiques Pures et Appliqu\u00e9es"},{"issue":"4","key":"2024111314110490500_qkae038-B38","doi-asserted-by":"publisher","first-page":"1040","DOI":"10.1214\/aos\/1176345969","article-title":"Optimal global rates of convergence for nonparametric regression","volume":"10","author":"Stone","year":"1982","journal-title":"Annals of Statistics"},{"key":"2024111314110490500_qkae038-B39","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4757-2545-2","volume-title":"Weak convergence and empirical processes","author":"Vaart","year":"1996"},{"issue":"523","key":"2024111314110490500_qkae038-B40","doi-asserted-by":"publisher","first-page":"1228","DOI":"10.1080\/01621459.2017.1319839","article-title":"Estimation and inference of heterogeneous treatment effects using random forests","volume":"113","author":"Wager","year":"2018","journal-title":"Journal of the American Statistical Association"},{"key":"2024111314110490500_qkae038-B42","doi-asserted-by":"publisher","first-page":"103","DOI":"10.1016\/j.neunet.2017.07.002","article-title":"Error bounds for approximations with deep ReLU networks","volume":"94","author":"Yarotsky","year":"2017","journal-title":"Neural Networks"},{"key":"2024111314110490500_qkae038-B43","author":"Yarotsky","year":"2018"},{"issue":"1","key":"2024111314110490500_qkae038-B44","doi-asserted-by":"publisher","first-page":"74","DOI":"10.1093\/nsr\/nwy108","article-title":"Deep forest","volume":"6","author":"Zhou","year":"2019","journal-title":"National Science Review"}],"container-title":["Journal of the Royal Statistical Society Series B: Statistical Methodology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/jrsssb\/article-pdf\/86\/5\/1435\/60648574\/qkae038.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jrsssb\/article-pdf\/86\/5\/1435\/60648574\/qkae038.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,13]],"date-time":"2024-11-13T14:11:39Z","timestamp":1731507099000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jrsssb\/article\/86\/5\/1435\/7679634"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,22]]},"references-count":42,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2024,5,22]]},"published-print":{"date-parts":[[2024,11,13]]}},"URL":"https:\/\/doi.org\/10.1093\/jrsssb\/qkae038","relation":{},"ISSN":["1369-7412","1467-9868"],"issn-type":[{"value":"1369-7412","type":"print"},{"value":"1467-9868","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2024,11]]},"published":{"date-parts":[[2024,5,22]]}}}