{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,14]],"date-time":"2026-10-14T16:49:17Z","timestamp":1791996557393,"version":"4.4.0"},"reference-count":54,"publisher":"Informa UK Limited","license":[{"start":{"date-parts":[[2026,10,14]],"date-time":"2026-10-14T00:00:00Z","timestamp":1791936000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/doi.org\/10.1080\/policies-text-data-mining"}],"content-domain":{"domain":["www.tandfonline.com"],"crossmark-restriction":true},"short-container-title":["Journal of the American Statistical Association"],"DOI":"10.1080\/01621459.2026.2743842","type":"journal-article","created":{"date-parts":[[2026,10,14]],"date-time":"2026-10-14T16:20:47Z","timestamp":1791994847000},"page":"1-88","update-policy":"https:\/\/doi.org\/10.1080\/tandf_crossmark_01","source":"Crossref","is-referenced-by-count":0,"title":["Online covariance estimation for stochastic gradient descent under Markovian sampling"],"prefix":"10.1080","author":[{"given":"Abhishek","family":"Roy","sequence":"first","affiliation":[{"name":"Department of Statistics, Texas A&M University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Krishnakumar","family":"Balasubramanian","sequence":"additional","affiliation":[{"name":"Department of Statistics, University of California","place":["Davis"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"301","published-online":{"date-parts":[[2026,10,14]]},"reference":[{"key":"e_1_3_1_2_1","unstructured":"B. Agrawalla K. Balasubramanian and P. Ghosal. High-dimensional central limit theorems for linear functionals of online least-squares SGD. arXiv preprint arXiv:2302.09727 2023."},{"key":"e_1_3_1_3_1","unstructured":"A. Anastasiou K. Balasubramanian and M. A. Erdogdu. Normal approximation for stochastic gradient descent via non-asymptotic rates of martingale CLT. In Conference on Learning Theory pages 115\u2013137. PMLR 2019."},{"key":"e_1_3_1_4_1","doi-asserted-by":"crossref","unstructured":"S. Andradottir. A projected stochastic approximation algorithm. In 1991 Winter Simulation Conference Proceedings. pages 954\u2013955. IEEE Computer Society 1991.","DOI":"10.1109\/WSC.1991.185710"},{"key":"e_1_3_1_5_1","doi-asserted-by":"crossref","unstructured":"C. Andrieu \u00c9. Moulines and P. Priouret. Stability of stochastic approximation under verifiable conditions. SIAM Journal on Control and Optimization 44(1):283\u2013312 2005.","DOI":"10.1137\/S0363012902417267"},{"key":"e_1_3_1_6_1","doi-asserted-by":"crossref","unstructured":"H. Asi and J. C. Duchi. Stochastic (approximate) proximal point methods: Convergence optimality and adaptivity. SIAM Journal on Optimization 2019.","DOI":"10.1137\/18M1230323"},{"key":"e_1_3_1_7_1","doi-asserted-by":"crossref","unstructured":"R. Askanazi F. X. Diebold F. Schorfheide and M. Shin. On the comparison of interval forecasts. Journal of Time Series Analysis 39(6):953\u2013965 2018.","DOI":"10.1111\/jtsa.12426"},{"key":"e_1_3_1_8_1","doi-asserted-by":"crossref","unstructured":"P. Bartlett. Learning with a slowly changing distribution. In Proceedings of the fifth annual workshop on Computational learning theory pages 243\u2013252 1992.","DOI":"10.1145\/130385.130412"},{"key":"e_1_3_1_9_1","unstructured":"A. Benveniste M. M\u00e9tivier and P. Priouret. Adaptive algorithms and stochastic approximations volume 22. Springer Science & Business Media 2012."},{"key":"e_1_3_1_10_1","unstructured":"Y. Cai C. Daskalakis and C. Papadimitriou. Optimum statistical estimation with strategic data sources. In Conference on Learning Theory pages 280\u2013296. PMLR 2015."},{"key":"e_1_3_1_11_1","unstructured":"J. Chee H. Kim and P. Toulis. \u201cPlus\/minus the learning rate\u201d: Easy and scalable statistical inference with SGD. In 26th International Conference on Artificial Intelligence and Statistics (AISTATS) 2023."},{"key":"e_1_3_1_12_1","doi-asserted-by":"crossref","unstructured":"H. Chen C. Wu and Y. Zhu. Continuous-time stochastic approximation procedure with randomly varying truncations. Acta Mathematica Scientia 7(1):43\u201355 1987.","DOI":"10.1016\/S0252-9602(18)30487-9"},{"key":"e_1_3_1_13_1","doi-asserted-by":"crossref","unstructured":"H. Chen W. Lu and R. Song. Statistical inference for online decision making via stochastic gradient descent. Journal of the American Statistical Association 116(534):708\u2013719 2021.","DOI":"10.1080\/01621459.2020.1826325"},{"key":"e_1_3_1_14_1","unstructured":"H.-F. Chen. Stochastic approximation algorithms with expanding truncations. Stochastic Approximation and Its Applications pages 25\u201393 2002."},{"key":"e_1_3_1_15_1","unstructured":"L. Chen G. Keilbar and W. B. Wu. Recursive quantile estimation: Non-asymptotic confidence bounds. Journal of Machine Learning Research 24(91):1\u201325 2023."},{"key":"e_1_3_1_16_1","doi-asserted-by":"crossref","unstructured":"X. Chen J. D. Lee X. T. Tong and Y. Zhang. Statistical inference for model parameters in stochastic gradient descent. Annals of Statistics 48(1):251\u2013273 2020.","DOI":"10.1214\/18-AOS1801"},{"key":"e_1_3_1_17_1","doi-asserted-by":"crossref","unstructured":"D. Davis D. Drusvyatskiy and L. Jiang. Asymptotic normality and optimality in nonsmooth stochastic approximation. arXiv preprint arXiv:2301.06632 2023.","DOI":"10.1214\/24-AOS2401"},{"key":"e_1_3_1_18_1","unstructured":"B. Delyon. Stochastic approximation with decreasing gain: Convergence and asymptotic theory. Unpublished lecture notes Universit\u00e9 de Rennes 26:39 2000."},{"key":"e_1_3_1_19_1","doi-asserted-by":"crossref","unstructured":"A. Dieuleveut A. Durmus and F. Bach. Bridging the gap between constant step size stochastic gradient descent and Markov chains. Annals of Statistics 48(3):1348\u20131382 2020.","DOI":"10.1214\/19-AOS1850"},{"key":"e_1_3_1_20_1","doi-asserted-by":"crossref","unstructured":"R. Douc E. Moulines P. Priouret and P. Soulier. Markov Chains. Springer 2018.","DOI":"10.1007\/978-3-319-97704-1"},{"key":"e_1_3_1_21_1","doi-asserted-by":"crossref","unstructured":"D. Drusvyatskiy and L. Xiao. Stochastic optimization with decision-dependent distributions. Mathematics of Operations Research 48(2):954\u2013998 2023.","DOI":"10.1287\/moor.2022.1287"},{"key":"e_1_3_1_22_1","doi-asserted-by":"crossref","unstructured":"J. C. Duchi and F. Ruan. Asymptotic optimality in stochastic optimization. Annals of Statistics 49(1):21\u201348 2021.","DOI":"10.1214\/19-AOS1831"},{"key":"e_1_3_1_23_1","doi-asserted-by":"crossref","unstructured":"Y. Fang. Scalable statistical inference for averaged implicit stochastic gradient descent. Scandinavian Journal of Statistics 46(4):987\u20131002 2019.","DOI":"10.1111\/sjos.12378"},{"key":"e_1_3_1_24_1","unstructured":"Y. Fang J. Xu and L. Yang. Online bootstrap confidence intervals for the stochastic gradient descent estimator. Journal of Machine Learning Research 2018."},{"key":"e_1_3_1_25_1","doi-asserted-by":"crossref","unstructured":"G. Fort. Central limit theorems for stochastic approximation with controlled Markov chain dynamics. ESAIM: Probability and Statistics 19:60\u201380 2015.","DOI":"10.1051\/ps\/2014013"},{"key":"e_1_3_1_26_1","doi-asserted-by":"crossref","unstructured":"T. Gneiting and A. E. Raftery. Strictly proper scoring rules prediction and estimation. Journal of the American statistical Association 102(477):359\u2013378 2007.","DOI":"10.1198\/016214506000001437"},{"key":"e_1_3_1_27_1","doi-asserted-by":"crossref","unstructured":"Y. Goldberg R. Song and M. R. Kosorok. Adaptive Q-learning. In From Probability to Statistics and Back: High-Dimensional Models and Processes\u2013A Festschrift in Honor of Jon A. Wellner pages 150\u2013162. Institute of Mathematical Statistics 2013.","DOI":"10.1214\/12-IMSCOLL911"},{"key":"e_1_3_1_28_1","doi-asserted-by":"crossref","unstructured":"M. Hardt N. Megiddo C. Papadimitriou and M. Wootters. Strategic classification. In Proceedings of the 2016 ACM Conference on Innovations in Theoretical Computer Science pages 111\u2013122 2016.","DOI":"10.1145\/2840728.2840730"},{"key":"e_1_3_1_29_1","unstructured":"B. Karimi B. Miasojedow E. Moulines and H.-T. Wai. Non-asymptotic analysis of biased stochastic approximation scheme. In Conference on Learning Theory pages 1944\u20131974. PMLR 2019."},{"key":"e_1_3_1_30_1","unstructured":"K. Khamaru Y. Deshpande T. Lattimore L. Mackey and M. J. Wainwright. Near-optimal inference in adaptive linear regression. arXiv preprint arXiv:2107.02266v3 2023."},{"key":"e_1_3_1_31_1","doi-asserted-by":"crossref","unstructured":"H. J. Kushner and G. G. Yin. Stochastic approximation algorithms and applications 1997.","DOI":"10.1007\/978-1-4899-2696-8"},{"key":"e_1_3_1_32_1","unstructured":"Q. Li and H.-T. Wai. State dependent performative prediction with stochastic approximation. In International Conference on Artificial Intelligence and Statistics pages 3164\u20133186. PMLR 2022."},{"key":"e_1_3_1_33_1","unstructured":"X. Li J. Liang X. Chang and Z. Zhang. Statistical estimation and online inference via local SGD. In Conference on Learning Theory pages 1613\u20131661. PMLR 2022."},{"key":"e_1_3_1_34_1","unstructured":"X. Li J. Liang and Z. Zhang. Online statistical inference for nonlinear stochastic approximation with Markovian data. arXiv preprint arXiv:2302.07690 2023a."},{"key":"e_1_3_1_35_1","unstructured":"X. Li W. Yang J. Liang Z. Zhang and M. I. Jordan. A statistical analysis of Polyak-Ruppert averaged Q-learning. In International Conference on Artificial Intelligence and Statistics pages 2207\u20132261. PMLR 2023b."},{"key":"e_1_3_1_36_1","doi-asserted-by":"crossref","unstructured":"F. Liang. Trajectory averaging for stochastic approximation MCMC algorithms. The Annals of Statistics 38(5):2823\u20132856 2010.","DOI":"10.1214\/10-AOS807"},{"key":"e_1_3_1_37_1","doi-asserted-by":"crossref","unstructured":"T. Liang and W. J. Su. Statistical inference for the population landscape via moment-adjusted stochastic gradients. Journal of the Royal Statistical Society Series B: Statistical Methodology 81(2):431\u2013456 2019.","DOI":"10.1111\/rssb.12313"},{"key":"e_1_3_1_38_1","unstructured":"R. Liu X. Chen and Z. Shang. Statistical inference with stochastic gradient methods under \u03d5 -mixing data. arXiv preprint arXiv:2302.12717 2023."},{"key":"e_1_3_1_39_1","unstructured":"C. Mendler-D\u00fcnner J. Perdomo T. Zrnic and M. Hardt. Stochastic optimization for performative prediction. Advances in Neural Information Processing Systems 33:4929\u20134939 2020."},{"key":"e_1_3_1_40_1","unstructured":"S. P. Meyn and R. L. Tweedie. Markov chains and stochastic stability. Springer Science & Business Media 2012."},{"key":"e_1_3_1_41_1","unstructured":"J. Perdomo T. Zrnic C. Mendler-D\u00fcnner and M. Hardt. Performative prediction. In International Conference on Machine Learning pages 7599\u20137609. PMLR 2020."},{"key":"e_1_3_1_42_1","doi-asserted-by":"crossref","unstructured":"B. T. Polyak and A. B. Juditsky. Acceleration of stochastic approximation by averaging. SIAM Journal on Control and Optimization 30(4):838\u2013855 1992.","DOI":"10.1137\/0330046"},{"key":"e_1_3_1_43_1","unstructured":"G. Qu and A. Wierman. Finite-time analysis of asynchronous stochastic approximation and Q-learning. In Conference on Learning Theory pages 3185\u20133205. PMLR 2020."},{"key":"e_1_3_1_44_1","unstructured":"P. Ramprasad Y. Li Z. Yang Z. Wang W. W. Sun and G. Cheng. Online bootstrap inference for policy evaluation in reinforcement learning. Journal of the American Statistical Association pages 1\u201314 2022."},{"key":"e_1_3_1_45_1","unstructured":"A. Roy and P. Mohapatra. Fairness Uncertainty Quantification: How certain are you that the model is fair? arXiv preprint arXiv:2304.13950 2023."},{"key":"e_1_3_1_46_1","doi-asserted-by":"crossref","unstructured":"Q.-M. Shao and Z.-S. Zhang. Berry\u2013Esseen bounds for multivariate nonlinear statistics with applications to M-estimators and stochastic gradient descent algorithms. Bernoulli 28(3):1548\u20131576 2022.","DOI":"10.3150\/21-BEJ1336"},{"key":"e_1_3_1_47_1","doi-asserted-by":"crossref","unstructured":"C. Shi R. Song W. Lu and R. Li. Statistical inference for high-dimensional models via recursive online-score estimation. Journal of the American Statistical Association 116(535):1307\u20131318 2021.","DOI":"10.1080\/01621459.2019.1710154"},{"key":"e_1_3_1_48_1","doi-asserted-by":"crossref","unstructured":"V. Solo. Stochastic approximation with dependent noise. Stochastic Processes and their Applications 13(2):157\u2013170 1982.","DOI":"10.1016\/0304-4149(82)90032-1"},{"key":"e_1_3_1_49_1","unstructured":"W. J. Su and Y. Zhu. HiGrad: Uncertainty quantification for online learning and stochastic approximation. Journal of Machine Learning Research 24(124):1\u201353 2023."},{"key":"e_1_3_1_50_1","doi-asserted-by":"crossref","unstructured":"P. Toulis and E. M. Airoldi. Asymptotic and finite-sample properties of estimators based on stochastic gradients. The Annals of Statistics 45(4):1694\u20131727 2017.","DOI":"10.1214\/16-AOS1506"},{"key":"e_1_3_1_51_1","unstructured":"Y. F. Wu W. Zhang P. Xu and Q. Gu. A finite-time analysis of two time-scale actor-critic methods. Advances in Neural Information Processing Systems 33:17617\u201317628 2020."},{"key":"e_1_3_1_52_1","unstructured":"L. Yu K. Balasubramanian S. Volgushev and M. Erdogdu. An analysis of constant step size SGD in the non-convex regime: Asymptotic normality and bias. Advances in Neural Information Processing 2021."},{"key":"e_1_3_1_53_1","unstructured":"K. Zhang L. Janson and S. Murphy. Statistical inference with M-estimators on adaptively collected data. Advances in Neural Information Processing Systems 34 2021."},{"key":"e_1_3_1_54_1","unstructured":"Y. Zhong T. Kuffner and S. Lahiri. Online bootstrap inference with nonconvex stochastic gradient descent estimator. arXiv preprint arXiv:2306.02205 2023."},{"key":"e_1_3_1_55_1","doi-asserted-by":"crossref","unstructured":"W. Zhu X. Chen and W. B. Wu. Online covariance matrix estimation in stochastic gradient descent. Journal of the American Statistical Association 118(541):393\u2013404 2023.","DOI":"10.1080\/01621459.2021.1933498"}],"container-title":["Journal of the American Statistical Association"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.tandfonline.com\/doi\/pdf\/10.1080\/01621459.2026.2743842","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.tandfonline.com\/doi\/full-xml\/10.1080\/01621459.2026.2743842","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.tandfonline.com\/doi\/pdf\/10.1080\/01621459.2026.2743842","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,14]],"date-time":"2026-10-14T16:21:44Z","timestamp":1791994904000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.tandfonline.com\/doi\/full\/10.1080\/01621459.2026.2743842"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10,14]]},"references-count":54,"alternative-id":["10.1080\/01621459.2026.2743842"],"URL":"https:\/\/doi.org\/10.1080\/01621459.2026.2743842","relation":{},"ISSN":["0162-1459","1537-274X"],"issn-type":[{"value":"0162-1459","type":"print"},{"value":"1537-274X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,14]]},"assertion":[{"value":"The publishing and review policy for this title is described in its Aims & Scope.","order":1,"name":"peerreview_statement","label":"Peer Review Statement"},{"value":"http:\/\/www.tandfonline.com\/action\/journalInformation?show=aimsScope&journalCode=uasa20","URL":"http:\/\/www.tandfonline.com\/action\/journalInformation?show=aimsScope&journalCode=uasa20","order":2,"name":"aims_and_scope_url","label":"Aim & Scope"},{"value":"2023-09-17","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-09-06","order":1,"name":"revised","label":"Revised","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-09-14","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-10-14","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}