{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T01:45:52Z","timestamp":1788831952084,"version":"build-2803163510"},"reference-count":52,"publisher":"Oxford University Press (OUP)","issue":"1","license":[{"start":{"date-parts":[[2020,11,23]],"date-time":"2020-11-23T00:00:00Z","timestamp":1606089600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/journals\/pages\/open_access\/funder_policies\/chorus\/standard_publication_model"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,2,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>We introduce a flexible framework for making inferences about general linear forms of a large matrix based on noisy observations of a subset of its entries. In particular, under mild regularity conditions, we develop a universal procedure to construct asymptotically normal estimators of its linear forms through double-sample debiasing and low-rank projection whenever an entry-wise consistent estimator of the matrix is available. These estimators allow us to subsequently construct confidence intervals for and test hypotheses about the linear forms. Our proposal was motivated by a careful perturbation analysis of the empirical singular spaces under the noisy matrix completion model which might be of independent interest. The practical merits of our proposed inference procedure are demonstrated on both simulated and real-world data examples.<\/jats:p>","DOI":"10.1111\/rssb.12400","type":"journal-article","created":{"date-parts":[[2020,11,24]],"date-time":"2020-11-24T00:58:44Z","timestamp":1606179524000},"page":"58-77","source":"Crossref","is-referenced-by-count":38,"title":["Statistical Inferences of Linear Forms for Noisy Matrix Completion"],"prefix":"10.1093","volume":"83","author":[{"given":"Dong","family":"Xia","sequence":"first","affiliation":[{"name":"Hong Kong University of Science and Technology , Hong Kong , China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ming","family":"Yuan","sequence":"additional","affiliation":[{"name":"Columbia University , New York, NY , USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2020,11,23]]},"reference":[{"issue":"1","key":"2023022408370081600_","doi-asserted-by":"crossref","first-page":"122","DOI":"10.1090\/S0002-9947-1941-0003498-3","article-title":"The accuracy of the gaussian approximation to the sum of independent variates","volume":"49","author":"Berry","year":"1941","journal-title":"Transactions of the American Mathematical Society"},{"issue":"4","key":"2023022408370081600_","doi-asserted-by":"crossref","first-page":"1956","DOI":"10.1137\/080738970","article-title":"A singular value thresholding algorithm for matrix completion","volume":"20","author":"Cai","year":"2010","journal-title":"SIAM Journal on Optimization"},{"issue":"2","key":"2023022408370081600_","doi-asserted-by":"crossref","first-page":"615","DOI":"10.1080\/02331888.2016.1265969","article-title":"Confidence intervals for high-dimensional linear regression: Minimax rates and adaptivity","volume":"45","author":"Cai","year":"2017","journal-title":"The Annals of Statistics"},{"issue":"1","key":"2023022408370081600_","doi-asserted-by":"crossref","first-page":"102","DOI":"10.1214\/14-AOS1267","article-title":"Rop: Matrix recovery via rank-one projections","volume":"43","author":"Cai","year":"2015","journal-title":"The Annals of Statistics"},{"issue":"1","key":"2023022408370081600_","doi-asserted-by":"crossref","first-page":"1493","DOI":"10.1214\/16-EJS1147","article-title":"Matrix completion via max-norm constrained optimization","volume":"10","author":"Cai","year":"2016","journal-title":"Electronic Journal of Statistics"},{"issue":"4","key":"2023022408370081600_","doi-asserted-by":"crossref","first-page":"1536","DOI":"10.1214\/15-AOS1426","article-title":"Geometric inference for general high-dimensional linear inverse problems","volume":"44","author":"Cai","year":"2016","journal-title":"The Annals of Statistics"},{"issue":"514","key":"2023022408370081600_","doi-asserted-by":"crossref","first-page":"621","DOI":"10.1080\/01621459.2015.1021005","article-title":"Structured matrix completion with applications to genomic data integration","volume":"111","author":"Cai","year":"2016","journal-title":"Journal of the American Statistical Association"},{"issue":"6","key":"2023022408370081600_","doi-asserted-by":"crossref","first-page":"925","DOI":"10.1109\/JPROC.2009.2035722","article-title":"Matrix completion with noise","volume":"98","author":"Candes","year":"2010","journal-title":"Proceedings of the IEEE"},{"issue":"6","key":"2023022408370081600_","doi-asserted-by":"crossref","first-page":"717","DOI":"10.1007\/s10208-009-9045-5","article-title":"Exact matrix completion via convex optimization","volume":"9","author":"Cand\u00e8s","year":"2009","journal-title":"Foundations of Computational Mathematics"},{"key":"2023022408370081600_","volume-title":"The power of convex relaxation: Near-optimal matrix completion","author":"Cand\u00e8s","year":"2009"},{"key":"2023022408370081600_","first-page":"1371","article-title":"An iterative hard thresholding estimator for low rank matrix recovery with explicit limiting distribution","volume":"28","author":"Carpentier","year":"2018","journal-title":"Statistica Sinica"},{"key":"2023022408370081600_","volume-title":"Uncertainty quantification for matrix compressed sensing and quantum tomography problems","author":"Carpentier","year":"2015"},{"issue":"4A","key":"2023022408370081600_","doi-asserted-by":"crossref","first-page":"2429","DOI":"10.3150\/17-BEJ933","article-title":"Adaptive confidence sets for matrix completion","volume":"24","author":"Carpentier","year":"2018","journal-title":"Bernoulli"},{"key":"2023022408370081600_","volume-title":"Nonconvex rectangular matrix completion via gradient descent without \ud835\udcc12,\u221e regularization","author":"Chen","year":"2019"},{"key":"2023022408370081600_","volume-title":"Fast low-rank estimation by projected gradient descent: General statistical and algorithmic guarantees","author":"Chen","year":"2015"},{"key":"2023022408370081600_","volume-title":"Noisy matrix completion: Understanding statistical guarantees for convex relaxation via nonconvex optimization","author":"Chen","year":"2019"},{"key":"2023022408370081600_","doi-asserted-by":"crossref","DOI":"10.1073\/pnas.1910053116","volume-title":"Inference and uncertainty quantification for noisy matrix completion","author":"Chen","year":"2019"},{"issue":"1","key":"2023022408370081600_","doi-asserted-by":"crossref","first-page":"C1","DOI":"10.1111\/ectj.12097","article-title":"Double\/debiased machine learning for treatment and structural parameters","volume":"21","author":"Chernozhukov","year":"2018","journal-title":"The Econometrics Journal"},{"issue":"1","key":"2023022408370081600_","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1137\/0707001","article-title":"The rotation of eigenvectors by a perturbation iii","volume":"7","author":"Davis","year":"1970","journal-title":"SIAM Journal on Numerical Analysis"},{"issue":"2","key":"2023022408370081600_","doi-asserted-by":"crossref","first-page":"303","DOI":"10.1137\/S0895479895290954","article-title":"The geometry of algorithms with orthogonality constraints","volume":"20","author":"Edelman","year":"1998","journal-title":"SIAM Journal on Matrix Analysis and Applications"},{"issue":"2","key":"2023022408370081600_","doi-asserted-by":"crossref","first-page":"160","DOI":"10.1080\/03461238.1956.10414946","article-title":"A moment inequality with an application to the central limit theorem","volume":"1956","author":"Esseen","year":"1956","journal-title":"Scandinavian Actuarial Journal"},{"issue":"1","key":"2023022408370081600_","first-page":"5602","article-title":"Optimal estimation and completion of matrices with biclustering structures","volume":"17","author":"Gao","year":"2016","journal-title":"The Journal of Machine Learning Research"},{"key":"2023022408370081600_","first-page":"2973","article-title":"Matrix completion has no spurious local minimum","author":"Ge","year":"2016","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"2","key":"2023022408370081600_","doi-asserted-by":"crossref","first-page":"133","DOI":"10.1023\/A:1011419012209","article-title":"Eigentaste: A constant time collaborative filtering algorithm","volume":"4","author":"Goldberg","year":"2001","journal-title":"Information Retrieval"},{"issue":"3","key":"2023022408370081600_","doi-asserted-by":"crossref","first-page":"1548","DOI":"10.1109\/TIT.2011.2104999","article-title":"Recovering low-rank matrices from few coefficients in any basis","volume":"57","author":"Gross","year":"2011","journal-title":"IEEE Transactions on Information Theory"},{"issue":"4","key":"2023022408370081600_","first-page":"19","article-title":"The movielens datasets: History and context","volume":"5","author":"Harper","year":"2016","journal-title":"ACM Transactions on Interactive Intelligent Systems (TIIS)"},{"issue":"1","key":"2023022408370081600_","first-page":"2869","article-title":"Confidence intervals and hypothesis testing for high-dimensional regression","volume":"15","author":"Javanmard","year":"2014","journal-title":"The Journal of Machine Learning Research"},{"issue":"6","key":"2023022408370081600_","doi-asserted-by":"crossref","first-page":"2980","DOI":"10.1109\/TIT.2010.2046205","article-title":"Matrix completion from a few entries","volume":"56","author":"Keshavan","year":"2010","journal-title":"IEEE Transactions on Information Theory"},{"issue":"7","key":"2023022408370081600_","first-page":"2057","article-title":"Matrix completion from noisy entries","volume":"11","author":"Keshavan","year":"2010","journal-title":"Journal of Machine Learning Research"},{"issue":"1","key":"2023022408370081600_","doi-asserted-by":"crossref","first-page":"282","DOI":"10.3150\/12-BEJ486","article-title":"Noisy low-rank matrix completion with general sampling distribution","volume":"20","author":"Klopp","year":"2014","journal-title":"Bernoulli"},{"issue":"6","key":"2023022408370081600_","doi-asserted-by":"crossref","first-page":"2936","DOI":"10.1214\/11-AOS926","article-title":"Von neumann entropy penalization and low-rank matrix estimation","volume":"39","author":"Koltchinskii","year":"2011","journal-title":"The Annals of Statistics"},{"issue":"53","key":"2023022408370081600_","first-page":"1757","article-title":"Optimal estimation of low rank density matrices","volume":"16","author":"Koltchinskii","year":"2015","journal-title":"Journal of Machine Learning Research"},{"issue":"5","key":"2023022408370081600_","doi-asserted-by":"crossref","first-page":"2302","DOI":"10.1214\/11-AOS894","article-title":"Nuclear-norm penalization and optimal rates for noisy low-rank matrix completion","volume":"39","author":"Koltchinskii","year":"2011","journal-title":"The Annals of Statistics"},{"key":"2023022408370081600_","first-page":"1638","article-title":"Universal low-rank matrix recovery from pauli measurements","author":"Liu","year":"2011","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2023022408370081600_","volume-title":"Implicit regularization in nonconvex statistical estimation: Gradient descent converges linearly for phase retrieval, matrix completion and blind deconvolution","author":"Ma","year":"2017"},{"issue":"12","key":"2023022408370081600_","doi-asserted-by":"crossref","first-page":"6939","DOI":"10.1109\/TIT.2015.2487541","article-title":"Volume ratio, sparsity, and minimaxity under unitarily invariant norms","volume":"61","author":"Ma","year":"2015","journal-title":"IEEE Transactions on Information Theory"},{"key":"2023022408370081600_","doi-asserted-by":"crossref","first-page":"111","DOI":"10.1016\/j.spl.2017.03.020","article-title":"On some extensions of bernstein\u2019s inequality for self-adjoint operators","volume":"127","author":"Minsker","year":"2017","journal-title":"Statistics & Probability Letters"},{"issue":"2","key":"2023022408370081600_","doi-asserted-by":"crossref","first-page":"1069","DOI":"10.1214\/10-AOS850","article-title":"Estimation of (near) low-rank matrices with noise and high-dimensional scaling","volume":"39","author":"Negahban","year":"2011","journal-title":"The Annals of Statistics"},{"key":"2023022408370081600_","first-page":"181","article-title":"Metric entropy of the grassmann manifold","volume":"34","author":"Pajor","year":"1998","journal-title":"Convex Geometric Analysis"},{"issue":"3","key":"2023022408370081600_","doi-asserted-by":"crossref","first-page":"471","DOI":"10.1137\/070697835","article-title":"Guaranteed minimum-rank solutions of linear matrix equations via nuclear norm minimization","volume":"52","author":"Recht","year":"2010","journal-title":"SIAM Review"},{"issue":"2","key":"2023022408370081600_","doi-asserted-by":"crossref","first-page":"887","DOI":"10.1214\/10-AOS860","article-title":"Estimation of high-dimensional low-rank matrices","volume":"39","author":"Rohde","year":"2011","journal-title":"The Annals of Statistics"},{"key":"2023022408370081600_","first-page":"863","article-title":"Calibrated elastic regularization in matrix completion","author":"Sun","year":"2012","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"4","key":"2023022408370081600_","doi-asserted-by":"crossref","first-page":"389","DOI":"10.1007\/s10208-011-9099-z","article-title":"User-friendly tail bounds for sums of random matrices","volume":"12","author":"Tropp","year":"2012","journal-title":"Foundations of Computational Mathematics"},{"issue":"3","key":"2023022408370081600_","doi-asserted-by":"crossref","first-page":"1166","DOI":"10.1214\/14-AOS1221","article-title":"On asymptotically optimal confidence regions and tests for high-dimensional models","volume":"42","author":"Van de Geer","year":"2014","journal-title":"The Annals of Statistics"},{"key":"2023022408370081600_","volume-title":"A unified computational and statistical framework for nonconvex low-rank matrix estimation","author":"Wang","year":"2016"},{"issue":"1","key":"2023022408370081600_","doi-asserted-by":"crossref","first-page":"99","DOI":"10.1007\/BF01932678","article-title":"Perturbation bounds in connection with singular value decomposition","volume":"12","author":"Wedin","year":"1972","journal-title":"BIT Numerical Mathematics"},{"issue":"11","key":"2023022408370081600_","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TIT.2019.2924900","article-title":"Confidence region of singular subspaces for high-dimensional and low-rank matrix regression","volume":"65","author":"Xia","year":"2019","journal-title":"IEEE Transactions on Information Theory"},{"key":"2023022408370081600_","volume-title":"Normal approximation and confidence region of singular subspaces","author":"Xia","year":"2019"},{"key":"2023022408370081600_","doi-asserted-by":"crossref","first-page":"1265","DOI":"10.1007\/s10208-018-09408-6","article-title":"On polynomial time methods for exact low-rank tensor completion","volume":"19","author":"Xia","year":"2019","journal-title":"Foundations of Computational Mathematics"},{"issue":"1","key":"2023022408370081600_","doi-asserted-by":"crossref","first-page":"217","DOI":"10.1111\/rssb.12026","article-title":"Confidence intervals for low dimensional parameters in high dimensional linear models","volume":"76","author":"Zhang","year":"2014","journal-title":"Journal of the Royal Statistical Society: Series B (Statistical Methodology)"},{"key":"2023022408370081600_","first-page":"559","article-title":"A nonconvex optimization framework for low rank matrix estimation","author":"Zhao","year":"2015","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2023022408370081600_","volume-title":"Convergence analysis for rectangular matrix completion using burer-monteiro factorization and gradient descent","author":"Zheng","year":"2016"}],"container-title":["Journal of the Royal Statistical Society Series B: Statistical Methodology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/rssb.12400","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1111\/rssb.12400","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/academic.oup.com\/jrsssb\/article-pdf\/83\/1\/58\/49324049\/jrsssb_83_1_58.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jrsssb\/article-pdf\/83\/1\/58\/49324049\/jrsssb_83_1_58.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,13]],"date-time":"2023-10-13T09:17:30Z","timestamp":1697188650000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jrsssb\/article\/83\/1\/58\/7050737"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,11,23]]},"references-count":52,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2020,11,23]]},"published-print":{"date-parts":[[2021,2,1]]}},"URL":"https:\/\/doi.org\/10.1111\/rssb.12400","relation":{},"ISSN":["1369-7412","1467-9868"],"issn-type":[{"value":"1369-7412","type":"print"},{"value":"1467-9868","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2021,2]]},"published":{"date-parts":[[2020,11,23]]}}}