{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T16:09:40Z","timestamp":1772726980497,"version":"3.50.1"},"reference-count":50,"publisher":"Informa UK Limited","issue":"550","license":[{"start":{"date-parts":[[2024,9,26]],"date-time":"2024-09-26T00:00:00Z","timestamp":1727308800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":["www.tandfonline.com"],"crossmark-restriction":true},"short-container-title":["Journal of the American Statistical Association"],"published-print":{"date-parts":[[2025,4,3]]},"DOI":"10.1080\/01621459.2024.2392904","type":"journal-article","created":{"date-parts":[[2024,8,22]],"date-time":"2024-08-22T14:56:53Z","timestamp":1724338613000},"page":"990-1001","update-policy":"https:\/\/doi.org\/10.1080\/tandf_crossmark_01","source":"Crossref","is-referenced-by-count":3,"title":["Natural Gradient Variational Bayes Without Fisher Matrix Analytic Calculation and Its Inversion"],"prefix":"10.1080","volume":"120","author":[{"given":"A.","family":"Godichon-Baggioni","sequence":"first","affiliation":[{"name":"Laboratoire de Probabilit\u00e9s","place":["Paris, France"]},{"name":"Sorbonne-Universit\u00e9","place":["Paris, France"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"D.","family":"Nguyen","sequence":"additional","affiliation":[{"name":"Department of Mathematics, Marist College","place":["Poughkeepsie"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"M.-N.","family":"Tran","sequence":"additional","affiliation":[{"name":"Business Analytics Discipline, The University of Sydney Business School","place":["Sydney, Australia"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"301","published-online":{"date-parts":[[2024,9,26]]},"reference":[{"key":"e_1_3_4_2_1","first-page":"1","article-title":"\u201cInformation-Theoretic Lower Bounds on the Oracle Complexity of Convex Optimization,\u201d in","volume":"22","author":"Agarwal A.","year":"2009","unstructured":"Agarwal, A., Wainwright, M. J., Bartlett, P., and Ravikumar, P. (2009), \u201cInformation-Theoretic Lower Bounds on the Oracle Complexity of Convex Optimization,\u201d in Advances in Neural Information Processing Systems (Vol. 22), pp. 1\u20139.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_4_3_1","doi-asserted-by":"publisher","DOI":"10.1162\/089976698300017746"},{"key":"e_1_3_4_4_1","doi-asserted-by":"publisher","DOI":"10.1137\/19M1261717"},{"key":"e_1_3_4_5_1","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.2017.1285773"},{"key":"e_1_3_4_6_1","doi-asserted-by":"publisher","DOI":"10.1137\/16M1080173"},{"key":"e_1_3_4_7_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10589-022-00442-3"},{"key":"e_1_3_4_8_1","doi-asserted-by":"publisher","DOI":"10.1111\/insr.12563"},{"key":"e_1_3_4_9_1","first-page":"1646","article-title":"\u201cSaga: A Fast Incremental Gradient Method with Support for Non-strongly Convex Composite Objectives,\u201d","author":"Defazio A.","year":"2014","unstructured":"Defazio, A., Bach, F., and Lacoste-Julien, S. (2014), \u201cSaga: A Fast Incremental Gradient Method with Support for Non-strongly Convex Composite Objectives,\u201d in Advances in Neural Information Processing Systems, pp. 1646\u20131654.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_4_10_1","first-page":"2121","article-title":"\u201cAdaptive Subgradient Methods for Online Learning and Stochastic Optimization,\u201d","volume":"12","author":"Duchi J.","year":"2011","unstructured":"Duchi, J., Hazan, E., and Singer, Y. (2011), \u201cAdaptive Subgradient Methods for Online Learning and Stochastic Optimization,\u201d Journal of Machine Learning Research, 12, 2121\u20132159.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_4_11_1","doi-asserted-by":"publisher","DOI":"10.1080\/10618600.2012.672784"},{"key":"e_1_3_4_12_1","unstructured":"Godichon-Baggioni A. and Werge N. (2023) \u201cOn Adaptive Stochastic Optimization for Streaming Data: A Newton\u2019s Method with o (dn) Operations \u201d arXiv preprint arXiv:2311.17753."},{"key":"e_1_3_4_13_1","volume-title":"Deep Learning","author":"Goodfellow I.","year":"2016","unstructured":"Goodfellow, I., Bengio, Y., and Courville, A. (2016), Deep Learning, Cambridge, MA: MIT Press."},{"key":"e_1_3_4_14_1","article-title":"\u201cPractical Variational Inference for Neural Networks,\u201d","volume":"24","author":"Graves A.","year":"2011","unstructured":"Graves, A. (2011), \u201cPractical Variational Inference for Neural Networks,\u201d in Advances in Neural Information Processing Systems (Vol. 24).","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_4_15_1","doi-asserted-by":"publisher","DOI":"10.1080\/10618600.2023.2262080"},{"key":"e_1_3_4_16_1","first-page":"1303","article-title":"\u201cStochastic Variational Inference,\u201d","volume":"14","author":"Hoffman M. D.","year":"2013","unstructured":"Hoffman, M. D., Blei, D. M., Wang, C., and Paisley, J. (2013), \u201cStochastic Variational Inference,\u201d Journal of Machine Learning Research, 14, 1303\u20131347.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_4_17_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4614-0406-4"},{"key":"e_1_3_4_18_1","first-page":"315","article-title":"\u201cAccelerating Stochastic Gradient Descent Using Predictive Variance Reduction,\u201d in","volume":"26","author":"Johnson R.","year":"2013","unstructured":"Johnson, R., and Zhang, T. (2013), \u201cAccelerating Stochastic Gradient Descent Using Predictive Variance Reduction,\u201d in Advances in Neural Information Processing Systems (Vol. 26), pp. 315\u2013323.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_4_19_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007665907178"},{"key":"e_1_3_4_20_1","first-page":"878","volume-title":"Artificial Intelligence and Statistics","author":"Khan M.","year":"2017","unstructured":"Khan, M., and Lin, W. (2017), \u201cConjugate-Computation Variational Inference: Converting Variational Inference in Non-conjugate Models to Inferences in Conjugate Models,\u201d in Artificial Intelligence and Statistics, pp. 878\u2013887, PMLR."},{"key":"e_1_3_4_21_1","unstructured":"Kingma D. P. and Ba J. (2014) \u201cAdam: A Method for Stochastic Optimization \u201d arXiv preprint arXiv:1412.6980."},{"key":"e_1_3_4_22_1","unstructured":"Kingma D. P. and Welling M. (2013) \u201cAuto-Encoding Variational Bayes \u201d arXiv preprint arXiv:1312.6114."},{"key":"e_1_3_4_23_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00362-021-01263-y"},{"key":"e_1_3_4_24_1","volume-title":"Stochastic Approximation and Recursive Algorithms and Applications","author":"Kushner H.","year":"2003","unstructured":"Kushner, H., and Yin, G. G. (2003), Stochastic Approximation and Recursive Algorithms and Applications (Vol. 35), New York: Springer."},{"key":"e_1_3_4_25_1","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/74.4.817"},{"key":"e_1_3_4_26_1","first-page":"1","volume-title":"2023 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2023)","author":"Lopatnikova A.","year":"2023","unstructured":"Lopatnikova, A., and Tran, M.-N. (2023), \u201cQuantum Variational Bayes on Manifolds,\u201d in 2023 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2023), pp. 1\u20135."},{"key":"e_1_3_4_27_1","unstructured":"Magris M. Shabani M. and Iosifidis A. (2022) \u201cExact Manifold Gaussian Variational Bayes \u201d arXiv preprint arXiv:2210.14598."},{"key":"e_1_3_4_28_1","first-page":"5776","article-title":"\u201cNew Insights and Perspectives on the Natural Gradient Method,\u201d","volume":"21","author":"Martens J.","year":"2020","unstructured":"Martens, J. (2020), \u201cNew Insights and Perspectives on the Natural Gradient Method,\u201d The Journal of Machine Learning Research, 21, 5776\u20135851.","journal-title":"The Journal of Machine Learning Research"},{"key":"e_1_3_4_29_1","first-page":"2408","volume-title":"International Conference on Machine Learning","author":"Martens J.","year":"2015","unstructured":"Martens, J., and Grosse, R. (2015), \u201cOptimizing Neural Networks with Kronecker-Factored Approximate Curvature,\u201d in International Conference on Machine Learning, pp. 2408\u20132417, PMLR."},{"key":"e_1_3_4_30_1","doi-asserted-by":"publisher","DOI":"10.1214\/22-STS875"},{"key":"e_1_3_4_31_1","volume-title":"Machine Learning: A Probabilistic Perspective","author":"Murphy K. P.","year":"2012","unstructured":"Murphy, K. P. (2012), Machine Learning: A Probabilistic Perspective, Cambridge, MA: MIT Press."},{"key":"e_1_3_4_32_1","first-page":"2613","volume-title":"International Conference on Machine Learning","author":"Nguyen L. M.","year":"2017","unstructured":"Nguyen, L. M., Liu, J., Scheinberg, K., and Tak\u00e1\u010d, M. (2017), \u201cSarah: A Novel Method for Machine Learning Problems Using Stochastic Recursive Gradient,\u201d in International Conference on Machine Learning, pp. 2613\u20132621, PMLR."},{"key":"e_1_3_4_33_1","first-page":"9397","article-title":"\u201cA Unified Convergence Analysis for Shuffling-Type Gradient Methods,\u201d","volume":"22","author":"Nguyen L. M.","year":"2021","unstructured":"Nguyen, L. M., Tran-Dinh, Q., Phan, D. T., Nguyen, P. H., and Van Dijk, M. (2021), \u201cA Unified Convergence Analysis for Shuffling-Type Gradient Methods,\u201d The Journal of Machine Learning Research, 22, 9397\u20139440.","journal-title":"The Journal of Machine Learning Research"},{"key":"e_1_3_4_34_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11222-017-9773-3"},{"key":"e_1_3_4_35_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0304-4149(98)00029-5"},{"key":"e_1_3_4_36_1","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.81.5461"},{"key":"e_1_3_4_37_1","first-page":"1530","volume-title":"International Conference on Machine Learning","author":"Rezende D.","year":"2015","unstructured":"Rezende, D., and Mohamed, S. (2015), \u201cVariational Inference with Normalizing Flows,\u201d in International Conference on Machine Learning, pp. 1530\u20131538, PMLR."},{"key":"e_1_3_4_38_1","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177729586"},{"key":"e_1_3_4_39_1","volume-title":"On-Line Learning in Neural Networks","author":"Saad D.","year":"2009","unstructured":"Saad, D. (2009), On-Line Learning in Neural Networks, Cambridge: Cambridge University Press."},{"key":"e_1_3_4_40_1","first-page":"689","volume-title":"International Conference on Artificial Intelligence and Statistics","author":"Salimbeni H.","year":"2018","unstructured":"Salimbeni, H., Eleftheriadis, S., and Hensman, J. (2018), \u201cNatural Gradients in Practice: Non-Conjugate Variational Inference in Gaussian Process Models,\u201d in International Conference on Artificial Intelligence and Statistics, pp. 689\u2013697, PMLR."},{"key":"e_1_3_4_41_1","doi-asserted-by":"publisher","DOI":"10.1162\/089976601750265045"},{"key":"e_1_3_4_42_1","doi-asserted-by":"publisher","DOI":"10.1002\/0471722138"},{"key":"e_1_3_4_43_1","unstructured":"Tan L. S. L. (2021) \u201cAnalytic Natural Gradient Updates for Cholesky Factor in Gaussian Variational Approximation \u201d arXiv preprint arXiv:2109.00375."},{"key":"e_1_3_4_44_1","first-page":"6145","volume-title":"International Conference on Machine Learning","author":"Tang D.","year":"2019","unstructured":"Tang, D., and Ranganath, R. (2019), \u201cThe Variational Predictive Natural Gradient,\u201d in International Conference on Machine Learning, pp. 6145\u20136154, PMLR."},{"key":"e_1_3_4_45_1","first-page":"1971","volume-title":"International Conference on Machine Learning","author":"Titsias M.","year":"2014","unstructured":"Titsias, M., L\u00e1zaro-Gredilla, M. (2014), \u201cDoubly Stochastic Variational Bayes for Non-conjugate Inference,\u201d in International Conference on Machine Learning, pp. 1971\u20131979, PMLR."},{"key":"e_1_3_4_46_1","doi-asserted-by":"publisher","DOI":"10.1080\/10618600.2019.1637747"},{"key":"e_1_3_4_47_1","doi-asserted-by":"publisher","DOI":"10.1080\/10618600.2017.1330205"},{"key":"e_1_3_4_48_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11222-021-10047-1"},{"key":"e_1_3_4_49_1","article-title":"\u201cBayesian Methods for Mixtures of Experts,\u201d","volume":"8","author":"Waterhouse S.","year":"1995","unstructured":"Waterhouse, S., MacKay, D., and Robinson, A. (1995), \u201cBayesian Methods for Mixtures of Experts,\u201d in Advances in Neural Information Processing Systems (Vol. 8).","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_4_50_1","first-page":"1","article-title":"\u201cBayes\u2013Newton Methods for Approximate Bayesian Inference with PSD Guarantees","volume":"24","author":"Wilkinson W. J.","year":"2023","unstructured":"Wilkinson, W. J., S\u00e4rkk\u00e4, S., and Solin, A. (2023), \u201cBayes\u2013Newton Methods for Approximate Bayesian Inference with PSD Guarantees,\u201d Journal of Machine Learning Research, 24, 1\u201350.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_4_51_1","unstructured":"Zeiler M D. (2012) \u201cAdadelta: An Adaptive Learning Rate Method \u201d arXiv preprint arXiv:1212.5701."}],"container-title":["Journal of the American Statistical Association"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.tandfonline.com\/doi\/pdf\/10.1080\/01621459.2024.2392904","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T15:09:39Z","timestamp":1772723379000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.tandfonline.com\/doi\/full\/10.1080\/01621459.2024.2392904"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,26]]},"references-count":50,"journal-issue":{"issue":"550","published-print":{"date-parts":[[2025,4,3]]}},"alternative-id":["10.1080\/01621459.2024.2392904"],"URL":"https:\/\/doi.org\/10.1080\/01621459.2024.2392904","relation":{},"ISSN":["0162-1459","1537-274X"],"issn-type":[{"value":"0162-1459","type":"print"},{"value":"1537-274X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,9,26]]},"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":"2023-12-26","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-04-25","order":1,"name":"revised","label":"Revised","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-06-17","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-09-26","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}