{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T00:15:50Z","timestamp":1789172150344,"version":"build-2803163510"},"reference-count":31,"publisher":"Oxford University Press (OUP)","issue":"3","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/pages\/standard-publication-reuse-rights"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,7,6]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>We propose CUSUM-Net, a nonparametric method for changepoint detection based on integral probability metrics and deep neural networks. Our approach learns a critic function by maximizing an aggregate CUSUM objective over candidate changepoints, thereby linking changepoint detection to optimization of two-sample integral probability metrics. The learned critic induces a one-dimensional representation on which changepoints are localized by a classical CUSUM scan. Unlike parametric procedures, CUSUM-Net accommodates complex, high-dimensional distributional changes and applies to a range of data modalities, including Euclidean data, symmetric positive-definite matrices, images and graphs. We establish excess-risk bounds for the learned critic under H\u00f6lder smoothness assumptions, with faster rates when the data exhibit low-dimensional manifold structure, and derive corresponding changepoint localization guarantees. Numerical experiments demonstrate the flexibility and effectiveness of the proposed method.<\/jats:p>","DOI":"10.1093\/biomet\/asag046","type":"journal-article","created":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T15:39:40Z","timestamp":1783438780000},"source":"Crossref","is-referenced-by-count":0,"title":["Integral probability metric-guided CUSUM-Net for nonparametric changepoint detection"],"prefix":"10.1093","volume":"113","author":[{"given":"Yunchen","family":"Li","sequence":"first","affiliation":[{"name":"School of Statistics, KLATASDS-MOE, East China Normal University , Shanghai 200062, \u00a0 52284404001@stu.ecnu.edu.cn","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guanghui","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Statistics and Data Science, LEBPS, LPMC, and KLMDASR, Nankai University ,Tianjin 300071, \u00a0 ghwang.nk@gmail.com","place":["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":["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":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2026,7,7]]},"reference":[{"key":"2026091119565757600_asag046-B1","author":"Arjovsky","year":"2017"},{"key":"2026091119565757600_asag046-B2","first-page":"1","article-title":"A kernel multiple change-point algorithm via model selection","volume":"20","author":"Arlot","year":"2019","journal-title":"J. Mach. Learn. Res."},{"key":"2026091119565757600_asag046-B3","doi-asserted-by":"crossref","first-page":"78","DOI":"10.1016\/j.jeconom.2009.10.020","article-title":"Common breaks in means and variances for panel data","volume":"157","author":"Bai","year":"2010","journal-title":"J. Economet"},{"key":"2026091119565757600_asag046-B4","author":"Bi\u0144kowski","year":"2018"},{"key":"2026091119565757600_asag046-B5","doi-asserted-by":"crossref","first-page":"139","DOI":"10.1214\/14-AOS1269","article-title":"Graph-based change-point detection","volume":"43","author":"Chen","year":"2015","journal-title":"Ann. Statist."},{"key":"2026091119565757600_asag046-B6","first-page":"1203","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":"Inf. Infer"},{"key":"2026091119565757600_asag046-B7","doi-asserted-by":"crossref","first-page":"475","DOI":"10.1111\/rssb.12079","article-title":"Multiple-change-point detection for high dimensional time series via sparsified binary segmentation","volume":"77","author":"Cho","year":"2015","journal-title":"J. R. Statist. Soc. B"},{"key":"2026091119565757600_asag046-B8","volume-title":"Limit Theorems in Change-Point Analysis","author":"Cs\u00f6rg\u0151","year":"1997"},{"key":"2026091119565757600_asag046-B9","doi-asserted-by":"crossref","first-page":"3312","DOI":"10.1214\/19-AOS1930","article-title":"Fr\u00e9chet change-point detection","volume":"48","author":"Dubey","year":"2020","journal-title":"Ann. Statist."},{"key":"2026091119565757600_asag046-B10","first-page":"723","article-title":"A kernel two-sample test","volume":"13","author":"Gretton","year":"2012","journal-title":"J. Mach. Learn. Res"},{"key":"2026091119565757600_asag046-B11","first-page":"1","article-title":"An error analysis of generative adversarial networks for learning distributions","volume":"23","author":"Huang","year":"2022","journal-title":"J. Mach. Learn. Res"},{"key":"2026091119565757600_asag046-B12","doi-asserted-by":"crossref","first-page":"2451","DOI":"10.1214\/15-AOS1347","article-title":"Uniform change point tests in high dimension","volume":"43","author":"Jirak","year":"2015","journal-title":"Ann. Statist."},{"key":"2026091119565757600_asag046-B13","author":"Kanrar","year":"2025"},{"key":"2026091119565757600_asag046-B14","doi-asserted-by":"crossref","first-page":"193","DOI":"10.1111\/rssb.12108","article-title":"The lasso for high dimensional regression with a possible change point","volume":"78","author":"Lee","year":"2016","journal-title":"J. R. Statist. Soc. B"},{"key":"2026091119565757600_asag046-B15","doi-asserted-by":"crossref","first-page":"933","DOI":"10.1111\/rssb.12375","article-title":"A unified data-adaptive framework for high dimensional change point detection","volume":"82","author":"Liu","year":"2020","journal-title":"J. R. Statist. Soc. B"},{"key":"2026091119565757600_asag046-B31","doi-asserted-by":"crossref","first-page":"e0196391","DOI":"10.1371\/journal.pone.0196391","article-title":"The Ryerson Audio-Visual Database of Emotional Speech and Song (RAVDESS): A dynamic, multimodal set of facial and vocal expressions in North American English.","volume":"13","author":"Livingstone","journal-title":"PloS one"},{"key":"2026091119565757600_asag046-B16","first-page":"1","article-title":"Random forests for change point detection","volume":"24","author":"Londschien","year":"2023","journal-title":"J. Mach. Learn. Res"},{"key":"2026091119565757600_asag046-B17","doi-asserted-by":"crossref","first-page":"334","DOI":"10.1080\/01621459.2013.849605","article-title":"A nonparametric approach for multiple change point analysis of multivariate data","volume":"109","author":"Matteson","year":"2014","journal-title":"J. Am. Statist. Assoc"},{"key":"2026091119565757600_asag046-B18","doi-asserted-by":"crossref","DOI":"10.1093\/biomet\/asaf024","article-title":"Nonparametric data segmentation in multivariate time series via joint characteristic functions","volume":"112","author":"McGonigle","year":"2025","journal-title":"Biometrika"},{"key":"2026091119565757600_asag046-B19","doi-asserted-by":"crossref","first-page":"429","DOI":"10.2307\/1428011","article-title":"Integral probability metrics and their generating classes of functions","volume":"29","author":"M\u00fcller","year":"1997","journal-title":"Adv. Appl. Prob"},{"key":"2026091119565757600_asag046-B20","author":"Pope","year":"2021"},{"key":"2026091119565757600_asag046-B21","doi-asserted-by":"crossref","first-page":"2153","DOI":"10.1109\/TIT.2017.2653803","article-title":"Riemannian Gaussian distributions on the space of symmetric positive definite matrices","volume":"63","author":"Said","year":"2017","journal-title":"IEEE Trans. Info. Theory"},{"key":"2026091119565757600_asag046-B22","first-page":"1875","article-title":"Nonparametric regression using deep neural networks with ReLU activation function","volume":"48","author":"Schmidt-Hieber","year":"2020","journal-title":"Ann. Statist"},{"key":"2026091119565757600_asag046-B23","doi-asserted-by":"crossref","first-page":"5174","DOI":"10.1109\/TSP.2024.3479274","article-title":"Practical and powerful kernel-based change-point detection","volume":"72","author":"Song","year":"2024","journal-title":"IEEE Trans. Sig. Proces"},{"key":"2026091119565757600_asag046-B24","doi-asserted-by":"crossref","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":"Ann. Statist."},{"key":"2026091119565757600_asag046-B25","doi-asserted-by":"crossref","first-page":"1282","DOI":"10.1214\/23-AOS2291","article-title":"Minimax rate of distribution estimation on unknown submanifolds under adversarial losses","volume":"51","author":"Tang","year":"2023","journal-title":"Ann. Statist."},{"key":"2026091119565757600_asag046-B26","doi-asserted-by":"crossref","first-page":"936","DOI":"10.1093\/jrsssb\/qkad048","article-title":"Computationally efficient and data-adaptive changepoint inference in high dimension","volume":"85","author":"Wang","year":"2023","journal-title":"J. R. Statist. Soc. B"},{"key":"2026091119565757600_asag046-B27","doi-asserted-by":"crossref","first-page":"57","DOI":"10.1111\/rssb.12243","article-title":"High dimensional change point estimation via sparse projection","volume":"80","author":"Wang","year":"2018","journal-title":"J. R. Statist. Soc. B"},{"key":"2026091119565757600_asag046-B28","doi-asserted-by":"crossref","first-page":"999","DOI":"10.1214\/24-AOS2380","article-title":"Change-point inference in high-dimensional regression models under temporal dependence","volume":"52","author":"Xu","year":"2024","journal-title":"Ann. Statist."},{"key":"2026091119565757600_asag046-B29","doi-asserted-by":"crossref","first-page":"1751","DOI":"10.1080\/01621459.2021.1884562","article-title":"Adaptive inference for change points in high-dimensional data","volume":"117","author":"Zhang","year":"2022","journal-title":"J. Am. Statist. Assoc"},{"key":"2026091119565757600_asag046-B30","doi-asserted-by":"crossref","first-page":"970","DOI":"10.1214\/14-AOS1210","article-title":"Nonparametric maximum likelihood approach to multiple change-point problems","volume":"42","author":"Zou","year":"2014","journal-title":"Ann. Statist."}],"container-title":["Biometrika"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/biomet\/advance-article-pdf\/doi\/10.1093\/biomet\/asag046\/68709006\/asag046.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/biomet\/article-pdf\/113\/3\/asag046\/68709006\/asag046.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/biomet\/article-pdf\/113\/3\/asag046\/68709006\/asag046.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T23:57:05Z","timestamp":1789171025000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/biomet\/article\/doi\/10.1093\/biomet\/asag046\/8726261"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":31,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2026,7,6]]}},"URL":"https:\/\/doi.org\/10.1093\/biomet\/asag046","relation":{},"ISSN":["0006-3444","1464-3510"],"issn-type":[{"value":"0006-3444","type":"print"},{"value":"1464-3510","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026]]},"published":{"date-parts":[[2026]]},"article-number":"asag046"}}